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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 776
    Prev
    Next
    INDEX
    Explanations

    descriptions of conflict and negative interactions, especially bullying or physical altercations

    oai_token-act-pair · gemini-2.0-flash

    bullying, fighting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     CreateTagHelper
    -0.72
     ModelExpression
    -0.68
    tinyos
    -0.65
    parsedMessage
    -0.63
    SerializedSize
    -0.63
    openha
    -0.62
    évaluateur
    -0.61
     ligiloj
    -0.61
    +#+#
    -0.61
    sibilité
    -0.61
    POSITIVE LOGITS
     violent
    0.59
    ModelBuilder
    0.49
     violento
    0.47
     bullying
    0.47
     violence
    0.46
     arresting
    0.45
    ťaž
    0.45
     Gewalt
    0.44
     cuchillo
    0.44
     thugs
    0.43
    Activations Density 1.242%

    No Known Activations