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. 7339
    Prev
    Next
    INDEX
    Explanations

    the term "exception" and related error messages in 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
    encodeWith
    -0.91
    PreferredItem
    -0.89
     GoogleFonts
    -0.84
    DockStyle
    -0.83
    AnchorStyles
    -0.79
     useRouter
    -0.78
    setViewportView
    -0.76
     Dietrich
    -0.76
     turg
    -0.76
    SMR
    -0.75
    POSITIVE LOGITS
    exception
    1.74
     exception
    1.71
     Exception
    1.70
    Exception
    1.58
     exceptions
    1.45
    EXCEPTION
    1.35
     Exceptions
    1.33
    exceptions
    1.32
    Exceptions
    1.24
     excep
    1.21
    Activations Density 0.056%

    No Known Activations