© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 63910
    Prev
    Next
    INDEX
    Explanations

    instances of escape or attempts to escape from confinement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    escape or break free

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referrerpolicy
    -0.45
    WebServlet
    -0.43
     fourrure
    -0.38
     JsonResponse
    -0.35
    ToProps
    -0.35
    cticut
    -0.34
    tinyos
    -0.33
    cof
    -0.33
     Schützen
    -0.32
     montanha
    -0.32
    POSITIVE LOGITS
     escape
    2.53
     escapes
    2.27
     escaped
    2.17
     Escape
    2.16
    escape
    2.11
     escaping
    2.05
    Escape
    2.03
     ESCAPE
    1.85
    escaped
    1.70
    escaping
    1.66
    Activations Density 0.127%

    No Known Activations