© 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. 8-GEMMASCOPE-RES-16K
    11. 721
    Prev
    Next
    INDEX
    Explanations

    variables related to some form of datum or value assignment and retrieval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dodo
    -0.87
    abestanden
    -0.78
     Sarmiento
    -0.74
     Tinker
    -0.73
     Ede
    -0.73
    rene
    -0.71
     irm
    -0.71
     incomplète
    -0.70
     ECO
    -0.70
    "+"
    -0.69
    POSITIVE LOGITS
     val
    1.51
     Val
    1.43
     VAL
    1.38
    VAL
    1.28
    val
    1.21
    Val
    1.21
     Valdez
    1.14
     valet
    1.06
     Valverde
    1.00
     Valky
    0.99
    Activations Density 0.067%

    No Known Activations