© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1408
    Prev
    Next
    INDEX
    Explanations

    references to hooks or hooking mechanisms in various contexts

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

    terms related to hooks and fastening mechanisms

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

    hook and fasteners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     ब्रेकडाउन
    -0.75
    Sì
    -0.73
     disambiguazione
    -0.72
    DockStyle
    -0.72
    ations
    -0.71
     متعلقه
    -0.70
     GenerationType
    -0.66
    aarrggbb
    -0.65
    ătoare
    -0.64
    Referències
    -0.63
    POSITIVE LOGITS
     hooks
    0.95
    hooks
    0.95
     Hooks
    0.92
     HOOK
    0.84
    HOOK
    0.81
    Hook
    0.80
    Hooks
    0.79
     Hook
    0.77
     Hooker
    0.77
    hook
    0.75
    Activations Density 0.016%

    No Known Activations