© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6184
    Prev
    Next
    INDEX
    Explanations

    references to mathematical or statistical models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.42
    AsUp
    -0.40
     baby
    -0.38
     living
    -0.38
     Baby
    -0.38
     oper
    -0.35
    KURZBESCHREIBUNG
    -0.35
    )})
    -0.33
    medskip
    -0.33
     wykonania
    -0.33
    POSITIVE LOGITS
    хьтан
    0.52
     Préférences
    0.50
    IsMutable
    0.49
    rungsseite
    0.48
     Вікіпе
    0.47
    Diweddarwch
    0.47
    Izvori
    0.47
    Personensuche
    0.46
    -------------</
    0.46
     surla
    0.45
    Activations Density 2.625%

    No Known Activations