© 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. 25-GEMMASCOPE-RES-16K
    11. 14843
    Prev
    Next
    INDEX
    Explanations

    elements related to digital content and e-publishing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fycat
    -0.54
    Datuak
    -0.54
    webcam
    -0.51
    histle
    -0.47
    apimachinery
    -0.44
     videa
    -0.44
    VideoView
    -0.44
     sợi
    -0.42
    brtc
    -0.41
     webcam
    -0.41
    POSITIVE LOGITS
     book
    2.38
     books
    2.28
     Book
    2.16
     Books
    2.11
    Book
    2.04
    books
    2.01
    book
    2.00
    Books
    2.00
     BOOK
    1.95
     BOOKS
    1.87
    Activations Density 0.885%

    No Known Activations