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

    Neuronpedia

    Jacobian LensNEW
    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. 5-GEMMASCOPE-RES-16K
    11. 963
    Prev
    Next
    INDEX
    Explanations

    syntactical structures and code patterns related to programming logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rhestr
    -0.94
     Shuk
    -0.91
     समीक्षक
    -0.81
     jid
    -0.81
     समीक्षाओं
    -0.80
     Molo
    -0.80
     itſelf
    -0.78
     NIM
    -0.78
     Italijani
    -0.78
     Roswell
    -0.77
    POSITIVE LOGITS
    mfenced
    0.75
     ever
    0.67
    ="#">
    0.62
     dis
    0.62
      
    0.61
    ↵
    0.61
    ,
    0.57
    <eos>
    0.56
     an
    0.56
     trạng
    0.56
    Activations Density 0.193%

    No Known Activations