© 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. 106569
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords, especially those indicating return types or function terminations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     &___
    -0.81
    DrawerToggle
    -0.78
     queſta
    -0.77
     dAtA
    -0.77
    principalColumn
    -0.75
    CloseOperation
    -0.69
     ſche
    -0.69
    featureID
    -0.68
     indígen
    -0.68
     BoxFit
    -0.68
    POSITIVE LOGITS
     void
    0.37
    ↵
    0.36
    void
    0.34
     RE
    0.34
     Re
    0.33
     N
    0.33
    ↵↵
    0.32
    N
    0.32
    thi
    0.31
    0
    0.31
    Activations Density 0.007%

    No Known Activations