© 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. 9-GEMMASCOPE-RES-131K
    11. 78001
    Prev
    Next
    INDEX
    Explanations

    terms related to muscle anatomy and movement

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

    biceps, triceps, quadriceps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.76
    Tikang
    -0.75
     snippetHide
    -0.75
    IntoConstraints
    -0.71
    出版年
    -0.71
    __':
    -0.68
    bootstrapcdn
    -0.68
    SequentialGroup
    -0.66
     betweenstory
    -0.65
    JSONException
    -0.64
    POSITIVE LOGITS
    ceps
    0.96
     اطلع
    0.78
    riceps
    0.59
    gnore
    0.58
    clearInterval
    0.48
     biceps
    0.42
    str
    0.38
     hùng
    0.32
     doba
    0.32
     branding
    0.30
    Activations Density 0.002%

    No Known Activations