© 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. 38377
    Prev
    Next
    INDEX
    Explanations

    references to families and family-related concepts

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

    family health and planning

    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
    DECREF
    -0.42
    UrlResolution
    -0.40
     retired
    -0.28
     zav
    -0.28
     sau
    -0.28
    **
    -0.28
     szen
    -0.28
    Principales
    -0.28
    TextHelper
    -0.27
     older
    -0.27
    POSITIVE LOGITS
     informée
    0.59
    clusal
    0.58
     estekak
    0.58
    家庭
    0.56
    transQ
    0.56
     esternos
    0.55
     strerror
    0.51
     家庭
    0.50
    argout
    0.49
     batt
    0.49
    Activations Density 0.018%

    No Known Activations