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. 16222
    Prev
    Next
    INDEX
    Explanations

    occurrences of error handling constructs, specifically catch blocks in programming code

    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
    lotl
    -0.52
    ::_('
    -0.51
     متحده
    -0.49
    jsonwebtoken
    -0.46
    lavia
    -0.45
     venues
    -0.45
    возможно
    -0.44
    omla
    -0.44
    QObject
    -0.44
    WireFormatLite
    -0.44
    POSITIVE LOGITS
    catch
    1.93
     catch
    1.93
     Catch
    1.63
    Catch
    1.49
     CATCH
    1.42
     catching
    1.39
     catches
    1.38
    CATCH
    1.24
    Catching
    1.00
     caught
    0.98
    Activations Density 0.017%

    No Known Activations