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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9655
    Prev
    Next
    INDEX
    Explanations

    references to browser compatibility and issues

    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
    cote
    -0.45
    SerializedName
    -0.42
     imageNamed
    -0.41
    Obituary
    -0.41
    ton
    -0.40
    リュ
    -0.40
    ValueGeneration
    -0.40
     thất
    -0.39
    Tazama
    -0.39
     Weldon
    -0.39
    POSITIVE LOGITS
     browser
    1.73
     browsers
    1.70
     Browser
    1.47
     Firefox
    1.39
    browser
    1.36
     Chrome
    1.35
    Browser
    1.32
     navegador
    1.30
     firefox
    1.27
     navigateur
    1.24
    Activations Density 0.188%

    No Known Activations