© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 14506
    Prev
    Next
    INDEX
    Explanations

    instances of the word "catch" and its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ish
    -0.36
    endif
    -0.34
    encoj
    -0.33
     gesteld
    -0.33
    cosse
    -0.31
     Suche
    -0.30
     Sahara
    -0.30
    ida
    -0.30
     propTypes
    -0.30
    a
    -0.30
    POSITIVE LOGITS
     catching
    0.98
     catch
    0.98
     Catch
    0.89
     catches
    0.88
     caught
    0.87
    Caught
    0.85
    Catch
    0.85
    catch
    0.84
     CATCH
    0.82
    caught
    0.82
    Activations Density 0.127%

    No Known Activations