© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-GEMMASCOPE-RES-16K
    11. 9952
    Prev
    Next
    INDEX
    Explanations

    references to the Od entity and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maho
    -0.96
    romyalgia
    -0.88
     Carmichael
    -0.84
     maxn
    -0.77
     Wulf
    -0.77
     **/
    -0.74
     createStore
    -0.73
     Arie
    -0.73
     Galway
    -0.71
     cardiaque
    -0.70
    POSITIVE LOGITS
     formData
    0.80
     Reng
    0.78
    ergic
    0.73
     Oleg
    0.72
    InstanceOf
    0.72
     Rodrigues
    0.71
    Leod
    0.70
    tus
    0.70
    seys
    0.70
    formData
    0.69
    Activations Density 1.018%

    No Known Activations