© 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. 11-GEMMASCOPE-RES-16K
    11. 6769
    Prev
    Next
    INDEX
    Explanations

    mentions of titles or names of works or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dürfte
    -0.42
    Đối
    -0.38
     gré
    -0.38
     húmedo
    -0.37
    érité
    -0.36
    Jur
    -0.36
     deberes
    -0.36
    lastIndex
    -0.35
     näin
    -0.35
     revisión
    -0.35
    POSITIVE LOGITS
     called
    1.06
    called
    0.95
    Called
    0.94
     Called
    0.93
     CALLED
    0.88
     named
    0.87
     bernama
    0.84
     chamado
    0.74
     llamado
    0.74
    叫做
    0.73
    Activations Density 0.340%

    No Known Activations