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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7278
    Prev
    Next
    INDEX
    Explanations

    the adjective "heavy" followed by a noun

    oai_token-act-pair · gemini-2.0-flash

    heavy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.11
     '\\;'
    -1.07
     Theſe
    -1.05
     ་་
    -1.02
     ―――――
    -0.99
     Efq
    -0.96
     itſelf
    -0.95
     Reſ
    -0.92
    $.
    
    -0.92
     ModelExpression
    -0.91
    POSITIVE LOGITS
     a
    0.69
     an
    0.68
    ↵↵
    0.67
    ;
    0.66
    n
    0.65
    <eos>
    0.65
    .
    0.63
     the
    0.63
     with
    0.62
    :
    0.59
    Activations Density 0.441%

    No Known Activations