Search:
Match:
2 results
Research#llm📝 BlogAnalyzed: Jan 3, 2026 07:50

Gemma Scope 2 Release Announced

Published:Dec 22, 2025 21:56
2 min read
Alignment Forum

Analysis

Google DeepMind's mech interp team is releasing Gemma Scope 2, a suite of Sparse Autoencoders (SAEs) and transcoders trained on the Gemma 3 model family. This release offers advancements over the previous version, including support for more complex models, a more comprehensive release covering all layers and model sizes up to 27B, and a focus on chat models. The release includes SAEs trained on different sites (residual stream, MLP output, and attention output) and MLP transcoders. The team hopes this will be a useful tool for the community despite deprioritizing fundamental research on SAEs.

Key Takeaways

Reference

The release contains SAEs trained on 3 different sites (residual stream, MLP output and attention output) as well as MLP transcoders (both with and without affine skip connections), for every layer of each of the 10 models in the Gemma 3 family (i.e. sizes 270m, 1b, 4b, 12b and 27b, both the PT and IT versions of each).

Product#Multimodal👥 CommunityAnalyzed: Jan 10, 2026 15:27

Mistral's Pixtral 12B: A New Multimodal AI Model

Published:Sep 11, 2024 19:47
1 min read
Hacker News

Analysis

The release of Pixtral 12B marks Mistral's entry into the multimodal AI space, potentially challenging existing players. Analyzing the performance and capabilities of this new model against competitors is crucial to understand its impact.
Reference

Mistral releases Pixtral 12B, its first multimodal model