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. 11-GEMMASCOPE-RES-16K
    6. 5621
    Prev
    Next
    INDEX
    Explanations

    various forms of errors in code and error handling statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mapStateToProps
    -0.89
    Xna
    -0.84
     Yorke
    -0.81
     stockings
    -0.79
    +#+#
    -0.79
    enance
    -0.78
    '}}
    -0.77
     Má
    -0.74
     Maho
    -0.73
     PCP
    -0.72
    POSITIVE LOGITS
    err
    1.48
     err
    1.10
    ERR
    0.83
     useRef
    0.80
     Gerr
    0.80
    errHandler
    0.80
     Вот
    0.73
    sec
    0.71
    ிரு
    0.70
    Tess
    0.70
    Activations Density 0.054%

    No Known Activations