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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 725
    Prev
    Next
    INDEX
    Explanations

    source code file paths and directory references in a programming context

    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
     much
    -0.61
    oplayer
    -0.60
    PathVariable
    -0.60
    much
    -0.58
    ThroughAttribute
    -0.57
    WithMany
    -0.56
    〕
    -0.56
    道的
    -0.55
    ону
    -0.54
     дописавши
    -0.54
    POSITIVE LOGITS
    src
    0.92
     Src
    0.91
     src
    0.85
     againſt
    0.75
    Src
    0.72
     himſelf
    0.70
     للمعارف
    0.69
     SRC
    0.68
     purpoſe
    0.67
     jacquard
    0.65
    Activations Density 0.035%

    No Known Activations