© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7796
    Prev
    Next
    INDEX
    Explanations

    mentions of layout-related terms in code or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
     }^{[
    -0.68
    <blockquote>
    -0.67
    +#+
    -0.64
     kär
    -0.62
     moks
    -0.60
    [
    -0.59
     cref
    -0.58
    sns
    -0.58
     Waller
    -0.57
     smtplib
    -0.57
    POSITIVE LOGITS
     layout
    2.68
     Layout
    2.58
     layouts
    2.51
    Layout
    2.31
     LAYOUT
    2.29
    layout
    2.21
    LAYOUT
    2.13
    layouts
    1.83
    Layouts
    1.75
    ayout
    1.65
    Activations Density 0.076%

    No Known Activations