© 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. 31-GEMMASCOPE-RES-16K
    11. 8858
    Prev
    Next
    INDEX
    Explanations

    code-related syntax such as function declarations and error handling constructs

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

    code syntax elements and structural patterns in programming languages.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.50
    SourceChecksum
    -0.47
    WebServlet
    -0.43
    GraphicsUnit
    -0.40
     Signalez
    -0.40
    addCriterion
    -0.38
    Hauptartikel
    -0.37
     гла
    -0.36
    ronique
    -0.36
    endmodule
    -0.35
    POSITIVE LOGITS
    await
    2.00
     await
    1.98
     awaits
    1.34
     awaiting
    1.34
     waiting
    1.08
     awaited
    1.07
     Waiting
    0.92
    Waiting
    0.90
    等待
    0.85
     wait
    0.85
    Activations Density 0.080%

    No Known Activations