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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 22446
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and equations involving variables and constants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AsUp
    -0.77
    recated
    -0.73
     Autorisations
    -0.68
     تضيفلها
    -0.65
    ffl
    -0.65
    iſten
    -0.65
    gnancy
    -0.64
    mpagne
    -0.64
    ſicht
    -0.64
     surla
    -0.64
    POSITIVE LOGITS
     solches
    0.36
     היתה
    0.35
     ancianos
    0.34
     Forderungen
    0.34
     zitten
    0.33
    ?
    0.33
     wesentlichen
    0.33
     solchen
    0.33
     dignité
    0.32
     europeos
    0.32
    Activations Density 0.064%

    No Known Activations