© 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. 3-GEMMASCOPE-RES-16K
    11. 4386
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "till" or its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    %)$
    -0.89
     beina
    -0.74
     Weih
    -0.71
     Maloney
    -0.68
     Krakowie
    -0.67
    QtWidgets
    -0.66
     Jonah
    -0.66
    (())
    -0.65
    haber
    -0.65
    Bson
    -0.65
    POSITIVE LOGITS
     till
    3.26
    Till
    3.03
     Till
    3.01
     TILL
    2.90
     until
    2.79
    until
    2.63
    till
    2.61
     Until
    2.59
     UNTIL
    2.57
    Until
    2.54
    Activations Density 0.077%

    No Known Activations