© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7669
    Prev
    Next
    INDEX
    Explanations

    elements of JavaScript code that relate to dynamic content handling and security practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pastikan
    -0.30
    elesaikan
    -0.28
     Bergh
    -0.28
     Thors
    -0.27
    geschlossen
    -0.27
     zelo
    -0.26
    義
    -0.26
    了一口
    -0.25
    habitude
    -0.25
    (")");
    -0.25
    POSITIVE LOGITS
     window
    1.32
    window
    1.28
     Window
    0.98
    document
    0.97
    Window
    0.97
     document
    0.93
    location
    0.88
     windows
    0.85
     WINDOW
    0.83
     jendela
    0.79
    Activations Density 0.287%

    No Known Activations