© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 12990
    Prev
    Next
    INDEX
    Explanations

    references to physical actions and interactions in a sports context

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

    physical collisions and injuries

    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
     arany
    -0.38
    ėse
    -0.35
     Commande
    -0.34
    页面存档备份
    -0.32
    ConstraintMaker
    -0.31
    ynchronously
    -0.30
     złota
    -0.29
     Propiedad
    -0.29
     DriverManager
    -0.29
    ükemmel
    -0.28
    POSITIVE LOGITS
     violent
    0.81
     bruising
    0.75
     collisions
    0.74
     brutality
    0.73
     bruises
    0.72
     violence
    0.72
     bruise
    0.69
     brutal
    0.69
     braw
    0.69
     toughness
    0.69
    Activations Density 0.028%

    No Known Activations