© 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. 21-GEMMASCOPE-RES-16K
    11. 3736
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to sensor technology and experimental setups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?
    -0.50
    mitteilung
    -0.48
    出版年
    -0.48
    Билгалдахарш
    -0.45
    Tracce
    -0.45
    inheritDoc
    -0.44
    허
    -0.44
    GenerationType
    -0.41
    athread
    -0.41
    postmedia
    -0.41
    POSITIVE LOGITS
     Figure
    2.88
    Figure
    2.75
     Fig
    2.62
    Fig
    2.54
     figure
    2.48
    figure
    2.39
     FIGURE
    2.27
    FIGURE
    2.21
     fig
    2.21
    fig
    2.17
    Activations Density 1.860%

    No Known Activations