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. 1099
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, players and the news articles about them.

    oai_token-act-pair · 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
    فق
    -0.46
     poor
    -0.43
    ah
    -0.42
     donne
    -0.41
     soportar
    -0.40
    yl
    -0.40
     relatifs
    -0.40
    ml
    -0.38
    give
    -0.38
    łk
    -0.38
    POSITIVE LOGITS
    zzleHttp
    0.85
    HostException
    0.84
     initComponents
    0.79
     дописавши
    0.78
    #+#
    0.77
     StatelessWidget
    0.76
     ExecuteAsync
    0.76
     referenties
    0.75
     saites
    0.75
    awtextra
    0.75
    Activations Density 1.842%

    No Known Activations