© 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. 12004
    Prev
    Next
    INDEX
    Explanations

    items related to medical and electrical components

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

    type or kind

    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
     ModelExpression
    -0.53
    UserScript
    -0.43
    transQ
    -0.42
    RTLD
    -0.41
    jsxFileName
    -0.41
    afficheront
    -0.41
     tampaknya
    -0.40
     jadx
    -0.40
    sehen
    -0.38
    無論
    -0.37
    POSITIVE LOGITS
     type
    1.10
     kind
    1.06
     نوع
    1.05
    一種
    1.05
    的一种
    1.02
    一种
    0.95
     jenis
    0.94
     types
    0.93
     סוג
    0.93
     rodzaj
    0.93
    Activations Density 0.168%

    No Known Activations