© 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. 42718
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to medical and biological processes

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

    postural stability, disordered gambling, infectivity

    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
    SharedDtor
    -0.63
    retudo
    -0.60
     Савезне
    -0.60
    новниш
    -0.59
    twimg
    -0.56
     Италијани
    -0.54
    Autoritní
    -0.53
    messageInfo
    -0.53
    principalTable
    -0.53
    беріга
    -0.52
    POSITIVE LOGITS
     iload
    0.42
     Erster
    0.38
    <0x83>
    0.36
     It
    0.36
    executeQuery
    0.36
     javafx
    0.32
    Liberty
    0.32
     RA
    0.32
    Taj
    0.31
    It
    0.31
    Activations Density 2.685%

    No Known Activations