3d4f350ab5
- Source: inbox/queue/2026-04-02-deepmind-negative-sae-results-pragmatic-interpretability.md - Domain: ai-alignment - Claims: 2, Entities: 1 - Enrichments: 1 - Extracted by: pipeline ingest (OpenRouter anthropic/claude-sonnet-4.5) Pentagon-Agent: Theseus <PIPELINE>
19 lines
No EOL
897 B
Markdown
19 lines
No EOL
897 B
Markdown
# Gemma Scope 2
|
|
|
|
**Type:** Research Program
|
|
**Organization:** Google DeepMind
|
|
**Domain:** AI Alignment / Mechanistic Interpretability
|
|
**Status:** Active (announced June 2025, release December 2025)
|
|
|
|
## Overview
|
|
|
|
Gemma Scope 2 is a full-stack interpretability suite for Gemma 3 models ranging from 270M to 27B parameters, producing approximately 110 petabytes of activation data.
|
|
|
|
## Strategic Context
|
|
|
|
Released alongside DeepMind's announcement of negative SAE results and pivot to pragmatic interpretability. The continued investment in interpretability infrastructure (despite deprioritizing SAE research specifically) signals that DeepMind remains committed to mechanistic interpretability tooling while becoming more selective about which techniques to pursue.
|
|
|
|
## Timeline
|
|
|
|
- **2025-06-01** — Announced in DeepMind's negative SAE results post
|
|
- **2025-12-XX** — Planned release date |