© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13760
    Prev
    Next
    INDEX
    Explanations

    code structure elements, specifically related to static functions and inline declarations

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

    "static" keyword in C code

    np_acts-logits-general · gemini-2.0-flash

    static code declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cstdio
    -0.53
    DoubleQuotes
    -0.51
     AssemblyCulture
    -0.51
    Życiorys
    -0.48
    upuesto
    -0.48
    Oto
    -0.47
    LLER
    -0.47
    Obrázky
    -0.46
    новништво
    -0.46
    URLException
    -0.45
    POSITIVE LOGITS
    struct
    0.71
     Roskov
    0.70
     enum
    0.67
    enum
    0.65
    tonsoft
    0.64
     Shakspeare
    0.63
     Monfieur
    0.62
    EDEFAULT
    0.61
     itſelf
    0.59
     protoimpl
    0.58
    Activations Density 0.200%

    No Known Activations