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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9892
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section, indicating a change in context or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     L
    -0.60
     G
    -0.54
     mergeFrom
    -0.52
     V
    -0.51
    libft
    -0.51
    ijan
    -0.50
     R
    -0.48
     f
    -0.47
     His
    -0.47
     t
    -0.47
    POSITIVE LOGITS
     ویکی‌پدیا
    0.85
     myſelf
    0.79
     Muses
    0.79
     怎样
    0.78
    http
    0.77
    findpost
    0.76
     dreamstime
    0.75
     Sarm
    0.74
     icmp
    0.72
     themſelves
    0.71
    Activations Density 0.034%

    No Known Activations