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. 6706
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations within the text

    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
    UnusedPrivate
    -0.60
     Leck
    -0.51
    ன்ன
    -0.48
     Steep
    -0.48
     tilbage
    -0.47
     typelib
    -0.46
     tient
    -0.45
     sentral
    -0.45
     Início
    -0.45
    hä
    -0.45
    POSITIVE LOGITS
     الرياضيه
    0.76
     propOrder
    0.75
     AssemblyCulture
    0.67
    rrggbb
    0.66
    TagMode
    0.65
     ModelExpression
    0.65
    انجليز
    0.64
    aarrggbb
    0.60
    +:+
    0.60
    MigrationBuilder
    0.60
    Activations Density 1.013%

    No Known Activations