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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 6795
    Prev
    Next
    INDEX
    Explanations

    references to data structures and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    pyx
    -0.61
     fermés
    -0.51
     noqa
    -0.51
    TYPED
    -0.48
    RTEE
    -0.48
     armée
    -0.48
     JpaRepository
    -0.48
     Wheatley
    -0.48
    expandindo
    -0.47
     sabia
    -0.46
    POSITIVE LOGITS
     CON
    1.97
    CON
    1.95
     Con
    1.93
    Con
    1.88
    con
    1.86
     con
    1.83
     kon
    1.80
     Кон
    1.79
     cons
    1.78
    Кон
    1.77
    Activations Density 0.339%

    No Known Activations