© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 11814
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Du" and its variants related to Duchenne muscular dystrophy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.35
    LabelTagHelper
    -0.34
     Keuangan
    -0.34
    tences
    -0.34
    MLLoader
    -0.33
    zegor
    -0.33
    PreInfinity
    -0.31
     végétale
    -0.30
     refroid
    -0.28
     serez
    -0.28
    POSITIVE LOGITS
     Du
    3.17
    Du
    3.14
    du
    3.11
     du
    3.09
     DU
    2.91
    DU
    2.72
    デュ
    2.11
     ду
    2.06
    杜
    1.95
     Ду
    1.94
    Activations Density 0.322%

    No Known Activations