© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15072
    Prev
    Next
    INDEX
    Explanations

    the word "that" in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "That" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    that followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poupée
    -0.41
     læng
    -0.40
     coopération
    -0.40
     cardiaque
    -0.40
    FieldNumber
    -0.40
     médicale
    -0.39
     spørs
    -0.39
     extérieure
    -0.39
     judiciaire
    -0.38
    leſs
    -0.38
    POSITIVE LOGITS
    THAT
    0.87
    that
    0.85
    That
    0.82
     that
    0.82
     THAT
    0.81
     That
    0.79
     que
    0.73
     που
    0.72
     tht
    0.71
     والتي
    0.69
    Activations Density 0.519%

    No Known Activations