© 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
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 2269
    Prev
    Next
    INDEX
    Explanations

    occurrences of semicolons and standard input/output libraries in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sumpay
    -0.52
    pecabe
    -0.52
    UrlEncoded
    -0.48
    Rüyada
    -0.47
    httphttps
    -0.47
     aérienne
    -0.46
    ớt
    -0.45
    WebElementEntity
    -0.44
     Económica
    -0.44
     ללא
    -0.44
    POSITIVE LOGITS
     للاسماء
    0.69
    stdc
    0.68
    stdio
    0.66
    iostream
    0.57
     '\\;'
    0.50
    cstdio
    0.46
     autorytatywna
    0.44
     الحره
    0.44
    complexContent
    0.43
    Portail
    0.43
    Activations Density 0.024%

    No Known Activations