© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 13207
    Prev
    Next
    INDEX
    Explanations

    words related to writing and editing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    openSession
    -0.37
    chufe
    -0.34
     powin
    -0.34
     kyse
    -0.32
    렀
    -0.32
    hadas
    -0.31
    していました
    -0.30
     sommes
    -0.30
     банка
    -0.30
     считать
    -0.30
    POSITIVE LOGITS
     worden
    0.90
     wordt
    0.85
     werden
    0.80
     được
    0.78
     wird
    0.73
     kasarigan
    0.73
    被人
    0.73
     werd
    0.71
     zostać
    0.69
     wurde
    0.68
    Activations Density 0.093%

    No Known Activations