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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 38422
    Prev
    Next
    INDEX
    Explanations

    references to callable objects and related programming concepts in code

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

    CTL code, names, questions

    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
    /***/
    -0.41
     ligiloj
    -0.40
     Markle
    -0.34
    createServer
    -0.33
    add
    -0.32
     eg
    -0.32
     který
    -0.30
    //
    -0.30
    Px
    -0.30
     cafe
    -0.30
    POSITIVE LOGITS
     Callable
    0.93
    MigrationBuilder
    0.82
    ChildScrollView
    0.80
     callable
    0.71
    prepareStatement
    0.71
     виправивши
    0.70
     autorytatywna
    0.65
     فريبيس
    0.65
     оригіналу
    0.64
    callable
    0.63
    Activations Density 0.007%

    No Known Activations