© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11899
    Prev
    Next
    INDEX
    Explanations

    technical jargon and terminology related to scientific research and mechanisms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Follows prepositions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    demonstrate theoretical findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    faßt
    -0.87
     idéia
    -0.85
     muß
    -0.79
     läßt
    -0.71
     daß
    -0.70
     Miß
    -0.65
     mußten
    -0.64
    luß
    -0.63
     Einfluß
    -0.63
     biß
    -0.62
    POSITIVE LOGITS
     microbiome
    0.86
     incentiv
    0.79
     impactful
    0.73
     nuanced
    0.71
     onboarding
    0.70
     CRISPR
    0.65
     agnostic
    0.64
    constexpr
    0.64
    ≲
    0.63
     curated
    0.63
    Activations Density 11.010%

    No Known Activations