© 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. 13083
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "squint" and its variations, as well as counts of the letter 'y'

    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
    casio
    -0.58
    APTER
    -0.54
     Blow
    -0.53
    ύ
    -0.51
    Kend
    -0.49
     Polity
    -0.48
     proceeds
    -0.48
    pola
    -0.47
     apri
    -0.47
    Blow
    -0.47
    POSITIVE LOGITS
    NameInMap
    0.94
    parsedMessage
    0.87
    DeleteBehavior
    0.86
     BoxFit
    0.86
    URLException
    0.85
     للاسماء
    0.85
     squeeze
    0.84
    PerformLayout
    0.80
     CreateTagHelper
    0.79
     squeezed
    0.77
    Activations Density 0.175%

    No Known Activations