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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15522
    Prev
    Next
    INDEX
    Explanations

    references to data fetching and application state management processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viewDidLoad
    -0.43
    hematics
    -0.36
     désolés
    -0.34
     kes
    -0.33
    plotlib
    -0.33
    Тарихы
    -0.30
    Principales
    -0.30
     Technik
    -0.30
     massima
    -0.30
     Voulez
    -0.30
    POSITIVE LOGITS
     context
    0.80
     Provider
    0.79
     useContext
    0.78
     Context
    0.77
     provider
    0.75
     Providers
    0.74
    Provider
    0.73
     providers
    0.71
    ImageContext
    0.71
    provider
    0.70
    Activations Density 0.019%

    No Known Activations