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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 9509
    Prev
    Next
    INDEX
    Explanations

    expressions related to mathematical operations and comparisons in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.47
    }};
    -0.47
    ++);
    -0.47
    ++;
    -0.46
     cív
    -0.46
     Crete
    -0.45
    ↵
    -0.43
    ;
    -0.42
     @"";
    -0.42
    。
    -0.42
    POSITIVE LOGITS
     ostavi
    0.81
    Rüyada
    0.80
     StringTokenizer
    0.79
    argout
    0.76
     تانيه
    0.73
    didSet
    0.72
    Viitteet
    0.71
    ⓧ
    0.71
     unknownFields
    0.70
    Архівовано
    0.70
    Activations Density 0.233%

    No Known Activations