© 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. 16-GEMMASCOPE-RES-65K
    11. 31901
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" used in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    that is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     however
    -0.81
    however
    -0.77
     entanto
    -0.70
    However
    -0.68
     However
    -0.68
     aber
    -0.66
     toutefois
    -0.63
    Initializable
    -0.62
     obstante
    -0.62
     echter
    -0.60
    POSITIVE LOGITS
    رشف
    0.80
     تانيه
    0.78
     שוליים
    0.72
    DoubleQuotes
    0.69
     Paglinawan
    0.66
    ungguhnya
    0.63
    何より
    0.62
    Brigitte
    0.59
    Enllaces
    0.58
    WithIOException
    0.58
    Activations Density 0.040%

    No Known Activations