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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 1979
    Prev
    Next
    INDEX
    Explanations

    the presence of special formatting tokens or structural elements in the text, indicative of document organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.85
     ModelExpression
    -0.81
    contentLoaded
    -0.81
    AccessFile
    -0.77
    AndEndTag
    -0.76
    principalColumn
    -0.76
     Wicidata
    -0.75
    findpost
    -0.72
     Paglinawan
    -0.69
     initComponents
    -0.68
    POSITIVE LOGITS
     Iso
    0.43
     $__
    0.42
    ngdoc
    0.42
     homology
    0.40
     ز
    0.39
    êmios
    0.39
     tox
    0.38
    ்
    0.38
    pubmed
    0.38
     Gras
    0.38
    Activations Density 0.085%

    No Known Activations