© 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. 13-GEMMASCOPE-RES-16K
    11. 4299
    Prev
    Next
    INDEX
    Explanations

    phrases related to the action of catching or grabbing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     واض
    -0.45
    𝓸
    -0.43
    𝓾
    -0.43
     Plano
    -0.41
     PAGES
    -0.41
    PFC
    -0.40
    rendon
    -0.40
    Pico
    -0.40
    𝓿
    -0.40
    𝓹
    -0.39
    POSITIVE LOGITS
     catch
    1.65
     Catch
    1.61
     catching
    1.56
    Catch
    1.50
    catch
    1.50
     catches
    1.45
     caught
    1.43
     CATCH
    1.41
    Caught
    1.29
     Caught
    1.28
    Activations Density 0.158%

    No Known Activations