© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 3001
    Prev
    Next
    INDEX
    Explanations

    repetitions and instances of washing in experimental procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Years
    -0.38
    audiovisuel
    -0.38
    years
    -0.35
     länge
    -0.35
    一场
    -0.34
    óta
    -0.33
     repeatedly
    -0.32
    StoredProcedure
    -0.31
     atlik
    -0.31
     hvert
    -0.31
    POSITIVE LOGITS
     times
    1.37
     TIMES
    1.02
     Times
    0.99
    times
    0.91
    Times
    0.89
    TIMES
    0.86
     Zeiten
    0.79
     tiempos
    0.71
     tijden
    0.70
     ProtoMessage
    0.68
    Activations Density 0.242%

    No Known Activations