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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 3405
    Prev
    Next
    INDEX
    Explanations

    the presence of specific structural elements in regulatory documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    例文帳に追加
    -0.65
    kloped
    -0.59
     Dostupné
    -0.54
    aarrggbb
    -0.53
     ISNI
    -0.47
    PreInfinity
    -0.47
    vertre
    -0.46
     mxArray
    -0.46
    ✭✭
    -0.46
    させていただ
    -0.45
    POSITIVE LOGITS
    }{
    0.69
     MediatR
    0.65
    --){
    0.65
     /\.
    0.63
    {\$
    0.62
     }{
    0.61
     Battista
    0.61
    ็จ
    0.61
    SKE
    0.60
    Repost
    0.60
    Activations Density 0.009%

    No Known Activations