Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 2257
    Prev
    Next
    INDEX
    Explanations

    references to aerosol sprays and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mắc
    -0.54
    Portail
    -0.53
    awtextra
    -0.53
    ScopeManager
    -0.52
    BrowserRouter
    -0.52
    templateUrl
    -0.51
    ledger
    -0.51
     Brodie
    -0.51
    MigrationBuilder
    -0.51
    onOptions
    -0.50
    POSITIVE LOGITS
     spray
    1.23
     spraying
    1.19
     Spray
    1.19
    Spray
    1.18
     sprayed
    1.11
     sprays
    1.11
    spray
    1.11
     injecting
    0.86
     sprayer
    0.82
    bootstrapcdn
    0.78
    Activations Density 0.402%

    No Known Activations