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. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13478
    Prev
    Next
    INDEX
    Explanations

    equations and labels typically found in mathematical or scientific documents

    oai_token-act-pair · gemini-2.0-flash

    label

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    BeginContext
    -0.88
     &___
    -0.82
     propOrder
    -0.74
    Rüyada
    -0.73
    ⓧ
    -0.73
    허
    -0.71
     autorytatywna
    -0.71
    はじめに
    -0.70
    rungsseite
    -0.69
    
    -0.69
    POSITIVE LOGITS
    haustible
    0.54
    ";}
    0.50
    ...');
    0.50
    URLException
    0.49
    ourable
    0.49
    quini
    0.48
    atuor
    0.48
    nóstico
    0.48
    ','.
    0.47
    NSIndexPath
    0.47
    Activations Density 3.345%

    No Known Activations