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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1030
    Prev
    Next
    INDEX
    Explanations

    references to people with a high activations for Michael Jackson, his defenders and his family

    oai_token-act-pair · gemini-2.0-flash

    proper nouns/names

    np_token-act-pair-logits · gemini-2.0-flash

    tributes and legacies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
     ModelExpression
    -0.88
    ]--;
    -0.88
    BibitemShut
    -0.88
    rrggbb
    -0.84
     againſt
    -0.84
     Chriftian
    -0.82
     itſelf
    -0.81
     Normdatei
    -0.81
     bereaved
    -0.81
     ſtate
    -0.79
    POSITIVE LOGITS
    (
    0.46
    m
    0.44
     -
    0.43
    -
    0.42
    /
    0.42
     (
    0.41
    M
    0.41
    чо
    0.40
     m
    0.40
    stand
    0.40
    Activations Density 4.024%

    No Known Activations