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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13024
    Prev
    Next
    INDEX
    Explanations

    exception handling keywords commonly used in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.85
     HasFactory
    -0.77
     surla
    -0.74
     Италијани
    -0.73
    RefNanny
    -0.71
    niſſe
    -0.70
     للاسماء
    -0.70
     PSL
    -0.69
    RTEX
    -0.69
    ſchaft
    -0.68
    POSITIVE LOGITS
    catch
    0.64
     ketat
    0.47
     catch
    0.45
    catchError
    0.44
    except
    0.44
     excepto
    0.43
     detallada
    0.41
     cortas
    0.41
     independientes
    0.40
     inesperado
    0.40
    Activations Density 0.024%

    No Known Activations