© 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. 3-GEMMASCOPE-RES-16K
    11. 1738
    Prev
    Next
    INDEX
    Explanations

    instances of the word "what" in various contexts

    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
    prefixer
    -0.69
     referenties
    -0.65
     mères
    -0.63
    ArrowToggle
    -0.59
    حياتها
    -0.58
     AssemblyTitle
    -0.57
     isolé
    -0.56
    iastes
    -0.56
     étoit
    -0.56
    وفاته
    -0.55
    POSITIVE LOGITS
     Réponses
    0.62
    AccessorTable
    0.59
     لما
    0.58
     ahogy
    0.53
    },{
    0.52
     what
    0.50
    WebServlet
    0.50
     indisponible
    0.49
    )];
    0.48
    rawQuery
    0.48
    Activations Density 0.236%

    No Known Activations