© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3381
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of a segment or paragraph

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

    much the [Capitalized Word]

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Kre
    -0.45
     en
    -0.45
     En
    -0.45
     san
    -0.43
     EN
    -0.41
     "";
    -0.39
     ];
    -0.39
    </code>
    -0.39
     Fay
    -0.38
    inde
    -0.37
    POSITIVE LOGITS
    ViewFeatures
    1.27
    GEBURTSDATUM
    1.19
    ?
    1.10
    1.10
    */

    1.06
    parsedMessage
    1.05
    ).

    1.05
    ConstraintMaker
    1.05
    .

    0.99
    ,

    0.97
    Activations Density 0.060%
    No Known Activations