© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 7246
    Prev
    Next
    INDEX
    Explanations

    programming syntax, particularly method definitions and return statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     चीज़ों
    -0.35
     polish
    -0.31
    CURS
    -0.31
    hrter
    -0.30
     mouseClicked
    -0.29
     projectId
    -0.28
    setCursor
    -0.28
    Returning
    -0.28
    价比
    -0.28
    endmodule
    -0.28
    POSITIVE LOGITS
     this
    1.00
    this
    0.88
     этим
    0.69
    ValueStyle
    0.66
     THIS
    0.66
     tämä
    0.65
     aquest
    0.65
     этого
    0.65
     этому
    0.64
     этой
    0.63
    Activations Density 0.178%

    No Known Activations