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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 3871
    Prev
    Next
    INDEX
    Explanations

    occurrences of error handling terms, particularly related to "catch" in programming contexts

    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
    CreateModel
    -0.67
    #+#
    -0.58
     løpet
    -0.56
    verhältnis
    -0.52
     artísticas
    -0.52
    crollView
    -0.51
    神経
    -0.51
    ndrome
    -0.50
    mäs
    -0.49
     Audiodateien
    -0.49
    POSITIVE LOGITS
    catch
    1.67
    CATCH
    1.03
    catcher
    1.01
    Catch
    1.01
     Catch
    0.92
     CATCH
    0.89
    oredCriteria
    0.86
    FailureListener
    0.85
     catch
    0.84
    igshid
    0.82
    Activations Density 0.038%

    No Known Activations