© 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. 3-GEMMASCOPE-RES-16K
    11. 1721
    Prev
    Next
    INDEX
    Explanations

    references to upcoming events or occurrences

    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
     But
    -0.56
    on
    -0.55
    Slf
    -0.54
     Cataloging
    -0.48
    -
    -0.48
    er
    -0.47
    F
    -0.46
    useEffect
    -0.46
    winston
    -0.45
     neust
    -0.45
    POSITIVE LOGITS
     upcoming
    2.88
    upcoming
    2.58
     Upcoming
    2.45
     forthcoming
    2.30
    Upcoming
    2.22
     impending
    1.71
     kommende
    1.68
     tomorrow
    1.52
     futura
    1.51
     future
    1.49
    Activations Density 0.036%

    No Known Activations