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. 18-GEMMASCOPE-RES-16K
    6. 8570
    Prev
    Next
    INDEX
    Explanations

    programming language structures and static declarations

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

    C code keyword: "static" or "void"

    np_acts-logits-general · gemini-2.0-flash

    static declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.72
     calldata
    -0.68
    bitField
    -0.67
    ExtendWith
    -0.66
    FunctionFlags
    -0.61
    ImageContext
    -0.61
     Signalez
    -0.61
    MethodManager
    -0.60
     للاسماء
    -0.60
     ElementRef
    -0.60
    POSITIVE LOGITS
    static
    1.02
     static
    0.82
     inline
    0.58
    extern
    0.58
    inline
    0.55
    void
    0.49
    
    0.49
     err
    0.48
    STATIC
    0.47
    静态
    0.47
    Activations Density 0.127%

    No Known Activations