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. 4260
    Prev
    Next
    INDEX
    Explanations

    complex relationships and interactions in various contexts

    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
    migrationBuilder
    -0.59
    LookAnd
    -0.56
    waitKey
    -0.54
    WriteLiteral
    -0.51
    fromCharCode
    -0.51
    DispatchToProps
    -0.50
     trấn
    -0.50
     dụ
    -0.50
     Италијани
    -0.48
    ElementException
    -0.48
    POSITIVE LOGITS
     complex
    2.80
     complexity
    2.71
     complicated
    2.64
    complex
    2.53
     complexities
    2.40
    Complex
    2.39
     Complex
    2.33
     COMPLEX
    2.31
     Complexity
    2.25
    complicated
    2.20
    Activations Density 0.680%

    No Known Activations