© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7742
    Prev
    Next
    INDEX
    Explanations

    HTML header tags and table structures within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.60
    enciaga
    -0.57
    varargin
    -0.55
    therford
    -0.54
     DbSet
    -0.54
    jacency
    -0.53
     мәкал
    -0.53
    vertx
    -0.52
    vaadin
    -0.52
    jeeling
    -0.52
    POSITIVE LOGITS
    <h3>
    2.72
    <h4>
    0.95
    <h5>
    0.88
    ###
    0.80
     ###
    0.79
    <h6>
    0.77
    </h3>
    0.77
    subsection
    0.73
    <table>
    0.54
    "},
    0.52
    Activations Density 0.024%

    No Known Activations