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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1232
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax or structure, particularly focusing on function or variable return statements

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

    punctuation marks and null references in code

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

    ");" code terminator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.97
    libft
    -0.73
    ItemBackground
    -0.70
     ویکی‌آمباردا
    -0.69
    tableFuture
    -0.68
     Efq
    -0.68
    omeness
    -0.67
    LikeLike
    -0.65
    ftagPool
    -0.64
     ujednoznacz
    -0.63
    POSITIVE LOGITS
    Kjelder
    0.69
    </h1>
    0.54
    __).
    0.47
     We
    0.47
    Chham
    0.47
    spyOn
    0.47
     amp
    0.45
    aton
    0.45
    enderror
    0.45
     Centre
    0.44
    Activations Density 0.022%

    No Known Activations