© 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. 24-GEMMASCOPE-RES-16K
    11. 6108
    Prev
    Next
    INDEX
    Explanations

    HTML header tags indicating sections and subsections in a document

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

    HTML heading tags (h1, h2, h3, h4, h5, h6)

    np_acts-logits-general · gemini-2.0-flash

    release notes or featured updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     لينك
    -0.79
    WebpackPlugin
    -0.77
    ſcher
    -0.76
    PreferredItem
    -0.74
    niſſe
    -0.73
    Spolja
    -0.73
    featureID
    -0.73
    chesse
    -0.71
     kasarigan
    -0.71
    ſammen
    -0.70
    POSITIVE LOGITS
    <h3>
    1.57
    <h2>
    0.86
    <h5>
    0.77
    <h4>
    0.77
    <h6>
    0.64
    <h1>
    0.64
    <strong>
    0.64
    <b>
    0.60
    subsection
    0.58
    <u>
    0.57
    Activations Density 0.027%

    No Known Activations