© 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. 22-GEMMASCOPE-RES-16K
    11. 10074
    Prev
    Next
    INDEX
    Explanations

    instances of the word "who" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Sanford
    -0.47
    full
    -0.45
    lt
    -0.43
     Seitz
    -0.41
    ert
    -0.41
    anye
    -0.41
     EST
    -0.41
    enta
    -0.40
    test
    -0.40
    retz
    -0.39
    POSITIVE LOGITS
     who
    1.09
     którzy
    0.93
     Who
    0.90
    Who
    0.90
     whom
    0.89
     kteří
    0.87
     queſta
    0.87
     quien
    0.83
    who
    0.83
    Quién
    0.82
    Activations Density 0.111%

    No Known Activations