© 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-2-2B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 6192
    Prev
    Next
    INDEX
    Explanations

    the word "who" in various grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     świą
    -0.69
    ArrowToggle
    -0.67
     Eis
    -0.66
     Merk
    -0.66
    らう
    -0.66
     fré
    -0.64
     paff
    -0.64
     Berech
    -0.63
    Peek
    -0.62
     رہ
    -0.62
    POSITIVE LOGITS
     who
    1.58
     WHO
    1.32
     Who
    1.29
    who
    1.18
    Who
    1.14
    osoever
    1.11
    WHO
    1.10
    Whoosh
    1.09
     którzy
    1.09
     quienes
    1.01
    Activations Density 0.074%

    No Known Activations