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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4800
    Prev
    Next
    INDEX
    Explanations

    declarations of variables and functions in programming code

    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
    ModelSerializer
    -0.72
    LookAnd
    -0.56
     समीक्षक
    -0.53
    ỡng
    -0.52
    uxxxx
    -0.52
    EndInit
    -0.49
    RTCK
    -0.49
    jenih
    -0.49
    莺
    -0.48
    Geografi
    -0.48
    POSITIVE LOGITS
     main
    3.39
    main
    3.12
    Main
    2.67
     Main
    2.55
     MAIN
    2.54
    MAIN
    2.52
     głów
    2.33
     principale
    2.19
     Haupt
    2.18
     hlavní
    2.17
    Activations Density 0.556%

    No Known Activations