© 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. 20-GEMMASCOPE-RES-131K
    11. 47675
    Prev
    Next
    INDEX
    Explanations

    elements related to physical movements and body positioning

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

    body extremities and movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Seed
    -0.42
     activado
    -0.38
    heça
    -0.38
    seed
    -0.35
     CITED
    -0.34
     visites
    -0.34
    Personal
    -0.34
     Idio
    -0.33
     Personal
    -0.33
     Personalis
    -0.33
    POSITIVE LOGITS
    IntoConstraints
    0.65
     limbs
    0.63
    QMetaType
    0.59
     CURIAM
    0.57
    FromNib
    0.56
     PeEnEo
    0.56
     NSCoder
    0.56
    __':
    0.55
    LayoutConstraint
    0.52
     propOrder
    0.52
    Activations Density 0.068%

    No Known Activations