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. 6718
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structures related to equations or expressions

    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
    gameserver
    -0.49
    таратура
    -0.49
    sizeCache
    -0.48
    ThroughAttribute
    -0.47
    DropTable
    -0.47
    évaluateur
    -0.47
    Pyx
    -0.45
     ModelExpression
    -0.45
     sext
    -0.44
     quæ
    -0.44
    POSITIVE LOGITS
    UnusedPrivate
    0.72
    Jîn
    0.62
     دیکھیے
    0.54
    EndInit
    0.54
     EconPapers
    0.53
    QObject
    0.53
     Hecht
    0.53
     المعرف
    0.53
     isComment
    0.52
    DebuggerNonUser
    0.51
    Activations Density 1.110%

    No Known Activations