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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6998
    Prev
    Next
    INDEX
    Explanations

    words related to athletic competitions, especially when used in conjunction with position or other ranking.

    oai_token-act-pair · gemini-2.0-flash

    Events and competitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    MigrationBuilder
    -0.66
    saraba
    -0.63
    Autoritní
    -0.59
    Personendaten
    -0.57
    fjspx
    -0.56
     HttpNotFound
    -0.53
     resourceCulture
    -0.53
    IVEREF
    -0.52
    onaceous
    -0.51
    INAS
    -0.51
    POSITIVE LOGITS
    DoubleQuotes
    0.60
     fudge
    0.57
    IsContent
    0.56
    UVWXYZ
    0.54
    LElement
    0.53
     препратки
    0.53
     blackout
    0.51
    Демографія
    0.51
     intptr
    0.51
     apothe
    0.50
    Activations Density 2.477%

    No Known Activations