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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 10197
    Prev
    Next
    INDEX
    Explanations

    verbs related to goals and intentions

    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
    expandindo
    -0.88
     Italijani
    -0.78
     AssemblyCulture
    -0.77
     AssemblyCompany
    -0.74
    RectangleBorder
    -0.73
     resourceCulture
    -0.73
     חיצוניים
    -0.72
    Diweddarwch
    -0.71
    EndProject
    -0.71
    PreferredItem
    -0.71
    POSITIVE LOGITS
     Профиль
    0.49
    的是
    0.47
     eventually
    0.47
     primarily
    0.45
     GenerationType
    0.45
     intends
    0.45
    nend
    0.45
     eventual
    0.45
    pekt
    0.44
    ounty
    0.43
    Activations Density 0.111%

    No Known Activations