© 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. 16333
    Prev
    Next
    INDEX
    Explanations

    terms related to health, materials, and functionality within scientific or technical contexts

    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
    NOPQRST
    -0.76
    AddTagHelper
    -0.60
     Enciclopedia
    -0.59
     Paglinawan
    -0.57
    contentLoaded
    -0.56
    numerusform
    -0.54
    Manbalar
    -0.53
    Tembelea
    -0.52
    PhysRev
    -0.52
     allt
    -0.52
    POSITIVE LOGITS
     quelconque
    0.88
     or
    0.86
     any
    0.84
     anything
    0.76
     anyone
    0.73
     whichever
    0.72
     '\\;'
    0.70
     anybody
    0.70
     atau
    0.68
     либо
    0.68
    Activations Density 0.622%

    No Known Activations