Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6766
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "static."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttino
    -0.91
    بيوتر
    -0.83
    ISupport
    -0.83
    charCodeAt
    -0.80
     Juno
    -0.79
     ControllerBase
    -0.78
     medulla
    -0.78
    omitempty
    -0.76
    XMLSchema
    -0.74
    valbard
    -0.73
    POSITIVE LOGITS
    STATIC
    1.43
     Static
    1.41
     STATIC
    1.32
    Static
    1.31
    static
    1.25
    静态
    1.22
     static
    1.17
    isStatic
    1.07
    statics
    0.97
     静
    0.91
    Activations Density 0.056%

    No Known Activations