© 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. 20-GEMMASCOPE-RES-16K
    11. 13738
    Prev
    Next
    INDEX
    Explanations

    HTML elements and structures in a document

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

    HTML, form, and script tags

    np_acts-logits-general · gemini-2.0-flash

    html tags and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '{@
    -0.67
    dafx
    -0.60
     发表于
    -0.59
     fact
    -0.58
    PYX
    -0.57
    发表于
    -0.55
    cshtml
    -0.54
    Portály
    -0.53
     certe
    -0.51
    SerializedName
    -0.51
    POSITIVE LOGITS
    RenderAtEndOf
    0.69
    ChildScrollView
    0.69
     الحره
    0.64
    writeFieldEnd
    0.63
     Jefus
    0.59
    </table>
    0.58
     Baillargeon
    0.58
    IntoConstraints
    0.57
    Hentet
    0.56
    MessageOf
    0.56
    Activations Density 0.116%

    No Known Activations