© 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. 16082
    Prev
    Next
    INDEX
    Explanations

    structured code or formatting elements within programming or markup languages

    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
    Gweler
    -0.57
     RoutedEventArgs
    -0.54
    UnsafeEnabled
    -0.54
    ----------
    -0.53
    ʲ
    -0.52
     AspNetCore
    -0.52
    stdc
    -0.51
     Wicidata
    -0.49
    kust
    -0.49
    Források
    -0.49
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
    EDEFAULT
    0.65
     ExecuteAsync
    0.63
    httphttps
    0.59
     виправивши
    0.56
    DockStyle
    0.54
     հղումներ
    0.54
    SharedDtor
    0.53
    $_['
    0.52
    ollectionView
    0.51
    Activations Density 0.107%

    No Known Activations