© 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. 10-GEMMASCOPE-RES-16K
    11. 12661
    Prev
    Next
    INDEX
    Explanations

    control flow statements, particularly those that alter the execution path of code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     devons
    -0.33
     voulons
    -0.32
     Defensa
    -0.32
     či
    -0.30
     ואת
    -0.30
    Garantía
    -0.30
    jící
    -0.30
    ורי
    -0.29
    ของคุณ
    -0.29
    ={{
    -0.29
    POSITIVE LOGITS
    break
    2.08
     break
    1.73
     Break
    1.54
    Break
    1.45
    BREAK
    1.39
     BREAK
    1.36
    breaks
    1.10
     breaks
    1.08
     Breaks
    1.02
     Breakthrough
    0.89
    Activations Density 0.062%

    No Known Activations