© 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. 10-GEMMASCOPE-RES-16K
    11. 5099
    Prev
    Next
    INDEX
    Explanations

    terms related to programming languages and libraries, especially in the context of graphical representation or data processing

    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
     möjligt
    -0.66
    prepareStatement
    -0.60
     tails
    -0.59
     diab
    -0.59
     Zjednoc
    -0.58
    hidupan
    -0.57
     douceur
    -0.57
     Dostupné
    -0.57
    strconv
    -0.57
    odiment
    -0.56
    POSITIVE LOGITS
     Gund
    1.09
    Bronnen
    1.04
     GS
    1.00
     gs
    0.94
     GV
    0.89
     kasarigan
    0.89
     GSC
    0.88
     Gad
    0.88
     GES
    0.86
     g
    0.86
    Activations Density 1.492%

    No Known Activations