© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5095
    Prev
    Next
    INDEX
    Explanations

    headings or sections in a document

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

    HTML heading tags (h1 to h6, h4)

    np_acts-logits-general · gemini-2.0-flash

    website headings and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.69
     gustaMe
    -0.67
     indígen
    -0.64
    parsedMessage
    -0.64
    OGND
    -0.63
     increí
    -0.63
     incrí
    -0.62
    rungsseite
    -0.62
    ulemon
    -0.61
    DeleteCommand
    -0.59
    POSITIVE LOGITS
    <h2>
    1.50
    <h4>
    1.38
    <h3>
    1.30
    <h1>
    1.27
    <h5>
    1.20
    <h6>
    0.84
    <b>
    0.81
    <strong>
    0.80
    <u>
    0.77
    <em>
    0.62
    Activations Density 0.124%

    No Known Activations