© 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. 23-GEMMASCOPE-RES-16K
    11. 15893
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to industry standards or medical treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bibliothèque
    -0.60
     poignée
    -0.57
     casquette
    -0.57
     poitrine
    -0.56
     réputation
    -0.55
     amitié
    -0.53
     leçon
    -0.53
     Révolution
    -0.52
     cathédrale
    -0.51
     poupée
    -0.50
    POSITIVE LOGITS
    kate
    0.84
     Bale
    0.83
     Wolfe
    0.81
    MCE
    0.80
     Tate
    0.80
    tune
    0.79
    ISE
    0.79
    IBE
    0.79
    UTE
    0.79
    rye
    0.79
    Activations Density 1.019%

    No Known Activations