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. 4-GEMMASCOPE-RES-16K
    6. 15806
    Prev
    Next
    INDEX
    Explanations

    elements related to fashion and styling advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MongoClient
    -0.57
    出版年
    -0.56
    ρους
    -0.55
     fabbrica
    -0.53
     лента
    -0.52
     prisonniers
    -0.52
     spectateurs
    -0.51
    getChildAt
    -0.50
     sœurs
    -0.49
     annuel
    -0.49
    POSITIVE LOGITS
     combinations
    1.00
     combination
    0.91
     Combination
    0.90
    combination
    0.88
    Combination
    0.88
     Combinations
    0.88
     combos
    0.86
    setVerticalGroup
    0.85
     combo
    0.84
    combinations
    0.82
    Activations Density 1.176%

    No Known Activations