Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 67563
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical analysis results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WireFormatLite
    -0.79
     disambiguazione
    -0.77
    帖最后由
    -0.73
    verifyException
    -0.73
    الحياه
    -0.73
    Hentet
    -0.73
     للمعارف
    -0.71
    +#+
    -0.69
     nahilalakip
    -0.69
    interopRequire
    -0.68
    POSITIVE LOGITS
     logros
    0.41
     fût
    0.41
     conformément
    0.40
     guantes
    0.38
     guías
    0.38
     aproximadamente
    0.38
     paneles
    0.37
     productivo
    0.37
     estándares
    0.37
     Economía
    0.37
    Activations Density 0.154%

    No Known Activations