© 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. 37369
    Prev
    Next
    INDEX
    Explanations

    references to research efforts and their outcomes.

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

    focused on or concentrated on

    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
     Infórmanos
    -0.45
    WebMethod
    -0.43
    dtos
    -0.40
    CrossRef
    -0.38
    sendEmail
    -0.38
    RTCF
    -0.38
    ⎠
    -0.37
    TableBody
    -0.37
    "?>
    -0.36
     Stedman
    -0.35
    POSITIVE LOGITS
     focus
    3.56
    focus
    3.08
     Focus
    3.02
     focusing
    2.97
    Focus
    2.95
     focuses
    2.94
     fokus
    2.86
     focused
    2.78
     Fokus
    2.67
     focussing
    2.67
    Activations Density 1.094%

    No Known Activations