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. 57316
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific equations and their equilibrium states

    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
    Geplaatst
    -0.71
     @"/
    -0.62
    Brainz
    -0.62
     ***!
    -0.60
    enderror
    -0.58
     CanadaChoose
    -0.57
     NSCoder
    -0.56
    nloa
    -0.54
     Signalez
    -0.53
    FunctionFlags
    -0.52
    POSITIVE LOGITS
     AppCompatTheme
    0.31
     Navidad
    0.30
     retenir
    0.29
    secta
    0.27
     dovol
    0.27
    FDRE
    0.27
     enough
    0.26
     sustained
    0.26
     steady
    0.26
     Flucht
    0.26
    Activations Density 0.328%

    No Known Activations