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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13983
    Prev
    Next
    INDEX
    Explanations

    HTML tags and elements in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML tags and mathematical symbols

    np_acts-logits-general · gemini-2.0-flash

    open state versus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.47
    principalColumn
    -0.46
     мәкал
    -0.44
    EnableWeb
    -0.44
    IContainer
    -0.44
    发表于
    -0.43
    oredCriteria
    -0.42
     ProtoMessage
    -0.41
    WEBPACK
    -0.41
    новниш
    -0.39
    POSITIVE LOGITS
    <h2>
    1.55
    <h3>
    1.53
    <h4>
    1.48
    <h5>
    1.34
    <h1>
    1.23
    <h6>
    1.19
    <table>
    0.88
    <caption>
    0.59
    <th>
    0.56
    <tr>
    0.54
    Activations Density 0.685%

    No Known Activations