AI Science Tracker
EN

University of Luxembourg

2 discoveries from 2020 to 2026

Discoveries

Gemma’s error-linked features rarely corrected answers under intervention

Source check: Source checked. Not independent scientific confirmation.

Finding: Interventions on sparse autoencoder features linked to errors changed answer preferences in two Gemma 3 models. Across question and option spans, selected features corrected 0.19% of initially wrong intervention events versus 0.06% for random active features. Effect directions were unstable when the prompt format or answer order changed.

Technology: Gemma 3; Gemma Scope 2 sparse autoencoders

Publication: Preprint · Test context: direct test. Catalog categories, not an evidence grade.

AI contribution
Gemma Scope 2 sparse autoencoders decode learned features in Gemma 3 1B and 4B. Feature intervention and matched random-active controls test causal sensitivity in question and answer option spans.
Test and result
Selected features changed answer margins more than randomly chosen active ones at question and option spans. Corrected proportions were 0.189% versus 0.058% of initially wrong intervention events. Matched format and option-order tests did not show a stable directional advantage.
Limitation / still unknown
The experiment studied eight multiple-choice datasets and selected layers in two model sizes. Events combine features, prompts and intervention settings, so they are not independent questions. The finding does not exclude mechanisms outside the tested features.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://arxiv.org/abs/2610.38067v1 · https://arxiv.org/html/2610.38067v1

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 21 Nov 2026. Review scope: arXiv v1 §§3–5.5 Table 5 and Appendix H.

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Prediction of the Vaccine-derived Poliovirus Outbreak Incidence: A Hybrid Machine Learning Approach.

Source check: Source checked. Not independent scientific confirmation.

Finding: The actual result is retrospective classification of serology/antibody patterns associated with historical Lao VDPV outbreaks; it does not establish prospective outbreak forecasting. External replication and prospective utility were not established in the reviewed material.

Technology: The actual result is retrospective classification of serology/antibody patterns associated with historical Lao VDPV outbreaks; it does not establish prospective outbreak forecasting.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
The actual result is retrospective classification of serology/antibody patterns associated with historical Lao VDPV outbreaks; it does not establish prospective outbreak forecasting.
Test and result
The actual result is retrospective classification of serology/antibody patterns associated with historical Lao VDPV outbreaks; it does not establish prospective outbreak forecasting.
Limitation / still unknown
External replication, causal effects and prospective utility were not established in the reviewed material.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.nature.com/articles/s41598-020-61853-y

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.