© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15560
    Prev
    Next
    INDEX
    Explanations

    HTML header tags, specifically `<h3>` and `<h4>`

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conform
    -0.82
     FormControl
    -0.77
    Datuak
    -0.77
    Conform
    -0.74
    ждународ
    -0.72
    jonal
    -0.71
    WindowConstants
    -0.71
     balk
    -0.70
     Bartol
    -0.69
    ductory
    -0.69
    POSITIVE LOGITS
    <h3>
    2.20
    Viitteet
    0.95
     ###
    0.93
    '));
    0.90
    </h3>
    0.88
     dieux
    0.87
    <h5>
    0.86
    */
    0.85
     \\
    0.82
    otis
    0.80
    Activations Density 0.103%

    No Known Activations