Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 4178
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "catch" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ayers
    -0.69
    isNullOrEmpty
    -0.63
    httphttps
    -0.61
     Landis
    -0.61
     Erskine
    -0.61
    sprechend
    -0.59
     Tabor
    -0.57
     Kelley
    -0.56
     Prima
    -0.56
     Fußballspieler
    -0.55
    POSITIVE LOGITS
     catch
    2.55
     Catch
    2.50
     catches
    2.41
     catching
    2.40
     CATCH
    2.39
    catch
    2.39
     caught
    2.38
    Catch
    2.27
    caught
    2.17
    Caught
    2.17
    Activations Density 0.043%

    No Known Activations