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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 52981
    Prev
    Next
    INDEX
    Explanations

    references to legal jurisdiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal jurisdiction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riwal
    -0.75
     Unwin
    -0.71
     Takashi
    -0.70
     chré
    -0.68
     Fears
    -0.66
     Bata
    -0.66
     Dani
    -0.65
    Portale
    -0.65
     DialogInterface
    -0.64
     Diener
    -0.64
    POSITIVE LOGITS
    BigDecimal
    1.02
     BigDecimal
    0.83
    вік
    0.64
     McCulloch
    0.63
    InputBorder
    0.62
    toFixed
    0.62
    Kund
    0.60
    
    0.60
    UPC
    0.58
     Kund
    0.58
    Activations Density 0.033%

    No Known Activations