© 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-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 3968
    Prev
    Next
    INDEX
    Explanations

    references to the word "who."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     itſelf
    -1.36
     myſelf
    -1.19
     Jefus
    -1.14
     themſelves
    -1.10
     $_"
    -1.09
     Anſ
    -1.07
     raiſ
    -1.05
     ſeveral
    -1.05
     Theſe
    -1.05
     himſelf
    -1.04
    POSITIVE LOGITS
     who
    2.03
    who
    1.88
     Who
    1.34
    Who
    1.34
     quien
    1.20
    WHO
    1.14
     WHO
    1.13
     qui
    1.11
     quién
    1.08
     quienes
    0.98
    Activations Density 0.253%

    No Known Activations