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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14259
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports victories and achievements

    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
    </thead>
    -0.47
    )=>{
    
    -0.47
     ویکی‌پدیای
    -0.46
     सकती
    -0.45
     shortly
    -0.44
     सकते
    -0.44
    OnPage
    -0.43
    WriteLiteral
    -0.43
     Shortly
    -0.43
    ")){
    
    -0.42
    POSITIVE LOGITS
     fince
    0.83
    stdc
    0.82
     since
    0.73
     BoxDecoration
    0.69
     dating
    0.66
    since
    0.65
    Dating
    0.65
     SINCE
    0.64
    patine
    0.63
    dating
    0.63
    Activations Density 0.185%

    No Known Activations