© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 14070
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Greg" or "Gregory."

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    
    -0.91
    sumowanie
    -0.85
     ActionListener
    -0.80
    Personensuche
    -0.78
     islanders
    -0.77
    Xaml
    -0.77
     giudi
    -0.76
     actionTypes
    -0.75
    isfile
    -0.74
    hassee
    -0.74
    POSITIVE LOGITS
     Greg
    1.57
     GREG
    1.41
    Greg
    1.38
     greg
    1.31
     Gregory
    1.23
    GREG
    1.20
     Gregorio
    1.18
    greg
    1.09
    Gregory
    1.07
    Gregg
    1.06
    Activations Density 0.006%

    No Known Activations