© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 11021
    Prev
    Next
    INDEX
    Explanations

    references to mathematical concepts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.55
     .
    -0.53
     {?>
    -0.47
    ’
    -0.46
    —
    -0.46
    wydd
    -0.46
    '
    -0.46
    __(/*!
    -0.46
     “
    -0.46
    “
    -0.46
    POSITIVE LOGITS
    onViewCreated
    0.83
    IntoConstraints
    0.74
    URLException
    0.74
    cèse
    0.72
    Geplaatst
    0.70
    âce
    0.66
     Mep
    0.66
    !("{}",
    0.65
     NSCoder
    0.65
     RoutedEventArgs
    0.64
    Activations Density 0.849%

    No Known Activations