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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 15658
    Prev
    Next
    INDEX
    Explanations

    instances of the word "catch" and its variations, indicating a focus on actions involving catching or grasping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.76
     Ayers
    -0.73
    isNullOrEmpty
    -0.67
     département
    -0.66
     Prima
    -0.62
     Kelley
    -0.60
     Landis
    -0.60
    illères
    -0.60
     Cowley
    -0.60
     sclerosis
    -0.59
    POSITIVE LOGITS
     Catch
    1.88
     CATCH
    1.84
     caught
    1.84
     catches
    1.83
     catch
    1.83
    catch
    1.79
     catching
    1.77
    Caught
    1.74
     Caught
    1.70
    CATCH
    1.70
    Activations Density 0.065%

    No Known Activations