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. 7149
    Prev
    Next
    INDEX
    Explanations

    text from the beginning of Wikipedia articles that often includes location names, alternate spellings, and political divisions

    oai_token-act-pair · gemini-2.0-flash

    born

    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
     kasarigan
    -0.75
     <=",
    -0.70
     resourceCulture
    -0.60
     guilty
    -0.57
    ToAction
    -0.56
     AssemblyTitle
    -0.56
    UnsafeEnabled
    -0.54
    atzung
    -0.50
    guilty
    -0.50
    EDEFAULT
    -0.48
    POSITIVE LOGITS
     насељу
    0.66
     Paglinawan
    0.63
    BeginContext
    0.63
    InitVars
    0.62
    Portail
    0.61
    Datuak
    0.56
    afficheront
    0.56
    帖最后由
    0.53
    ConverterFactory
    0.53
    OGND
    0.53
    Activations Density 1.530%

    No Known Activations