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. 21-GEMMASCOPE-RES-16K
    6. 7632
    Prev
    Next
    INDEX
    Explanations

    words related to cooking, particularly the act of cooking and recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     piti
    -0.45
    bootstrapcdn
    -0.45
    zarchiwizowane
    -0.41
    Ừ
    -0.41
     Est
    -0.41
    atum
    -0.40
    /*
    -0.40
     such
    -0.40
    
    -0.40
    啕
    -0.40
    POSITIVE LOGITS
    LAHOMA
    0.73
    reportWebVitals
    0.69
    TargetException
    0.69
     виправивши
    0.68
     MainAxisSize
    0.67
    books
    0.67
    cookieParser
    0.67
    expandindo
    0.66
    BagLayout
    0.66
    Viited
    0.66
    Activations Density 0.075%

    No Known Activations