© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11955
    Prev
    Next
    INDEX
    Explanations

    formal programming structure and class declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    `main` function declarations

    np_acts-logits-general · gemini-2.0-flash

    main function

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    +#+#
    -0.77
     للمعارف
    -0.73
     secco
    -0.59
     myſelf
    -0.59
     becauſe
    -0.58
    ⏟
    -0.58
     Monfieur
    -0.56
     Poitiers
    -0.56
     Reſ
    -0.56
     ſche
    -0.55
    POSITIVE LOGITS
     main
    1.55
    main
    1.45
    Main
    1.24
     Main
    1.19
     MAIN
    1.08
    MAIN
    1.05
     Haupt
    0.90
    主
    0.87
    メイン
    0.84
    mains
    0.80
    Activations Density 0.175%

    No Known Activations