© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13742
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs, specifically related to code structure and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kháu
    -0.60
     ChromeDriver
    -0.60
     htons
    -0.59
    SBATCH
    -0.58
    saraba
    -0.57
    TagMode
    -0.56
    ereien
    -0.55
    SuppressWarnings
    -0.54
     NavController
    -0.54
    autoreleasepool
    -0.53
    POSITIVE LOGITS
    endpush
    0.60
    مصادر
    0.57
    oa̍t
    0.55
     Réponses
    0.53
    utils
    0.53
    makeText
    0.52
    amodel
    0.52
    קישורים
    0.51
    parsedMessage
    0.51
    таратура
    0.51
    Activations Density 0.259%

    No Known Activations