© 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. 10859
    Prev
    Next
    INDEX
    Explanations

    symbols and constructs used in code, particularly related to function definitions and assertions

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

    C++ code or symbols

    np_acts-logits-general · gemini-2.0-flash

    code operators and NULL checks

    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
     CGFloat
    -0.59
     NSError
    -0.57
     boolean
    -0.57
     println
    -0.56
     actionMode
    -0.55
     Math
    -0.54
     betweenstory
    -0.51
     bal
    -0.51
     NSString
    -0.50
    LikeLike
    -0.50
    POSITIVE LOGITS
    static
    0.89
    NULL
    0.82
     NULL
    0.81
     reinterpret
    0.76
    ((
    0.73
     static
    0.73
    &(
    0.70
     egip
    0.67
    (*(
    0.67
     &(
    0.67
    Activations Density 0.341%

    No Known Activations