© 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. 0-GEMMASCOPE-RES-65K
    11. 9905
    Prev
    Next
    INDEX
    Explanations

    the recurring theme of "standing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    compar
    -0.52
     chaînes
    -0.49
     Phry
    -0.47
     Pliny
    -0.47
     mathematicians
    -0.47
     mexicano
    -0.47
     orgánica
    -0.47
     Dumnezeu
    -0.47
    ikirkan
    -0.45
    ấy
    -0.45
    POSITIVE LOGITS
    webElement
    0.79
    ara
    0.72
    ø
    0.71
    WithFormat
    0.71
    aras
    0.69
    ScopeManager
    0.69
     '{@
    0.68
     Larsen
    0.67
    
    0.67
    ара
    0.66
    Activations Density 0.032%

    No Known Activations