© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 11792
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to frameworks and structures in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     dyna
    -0.29
     Мекси
    -0.28
     UserController
    -0.28
     lav
    -0.28
    webdriver
    -0.27
     ramos
    -0.27
    actionMode
    -0.26
     je
    -0.25
     “
    -0.25
     tub
    -0.25
    POSITIVE LOGITS
     surla
    0.89
     CreateTagHelper
    0.82
    ConstraintMaker
    0.81
    ۜ
    0.70
     ProtoMessage
    0.70
     հղումներ
    0.70
     InputDecoration
    0.68
     Paglinawan
    0.68
    Билгалдахарш
    0.66
    Хьажоргаш
    0.66
    Activations Density 1.604%

    No Known Activations