© 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. 21668
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to programming or coding

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

    UI stage or scene

    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
     StatelessWidget
    -0.53
    routeProvider
    -0.42
    Trayectoria
    -0.38
    apuram
    -0.37
    jet
    -0.35
    psum
    -0.35
    gsl
    -0.33
     Schultz
    -0.33
    sika
    -0.33
    dracht
    -0.33
    POSITIVE LOGITS
    yntaxException
    0.63
    writeFieldEnd
    0.63
     Stage
    0.59
     stage
    0.56
     <=",
    0.55
    Stage
    0.53
     scene
    0.52
    invokeLater
    0.51
    AISSEE
    0.51
     Scene
    0.50
    Activations Density 0.002%

    No Known Activations