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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9651
    Prev
    Next
    INDEX
    Explanations

    phrases related to exceptions and error handling 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 @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    setViewportView
    -0.69
     AspNetCore
    -0.62
     useRouter
    -0.61
    implements
    -0.59
    roppo
    -0.58
    ernalia
    -0.58
    useppe
    -0.57
    isbol
    -0.57
    CHELL
    -0.57
     obligaciones
    -0.57
    POSITIVE LOGITS
    GEBURTSDATUM
    0.72
    ality
    0.69
    جمعیت
    0.67
    ince
    0.64
    alism
    0.64
    ally
    0.61
    Caught
    0.59
     Kenner
    0.58
     Roskov
    0.57
     XCTest
    0.57
    Activations Density 0.033%

    No Known Activations