© 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. 38-GEMMASCOPE-RES-16K
    11. 9611
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     solitary
    -0.31
    autorest
    -0.28
     bu
    -0.28
     berke
    -0.27
     فال
    -0.26
     se
    -0.26
     ge
    -0.25
     Gil
    -0.25
     Tori
    -0.25
    berry
    -0.25
    POSITIVE LOGITS
    InputBorder
    0.67
    recated
    0.66
     gyhoeddwyd
    0.62
    DrawerToggle
    0.60
    KommentareTeilen
    0.60
    ViewImports
    0.58
    webElementXpaths
    0.56
    ValueStyle
    0.56
     EconPapers
    0.54
    Distribuzione
    0.54
    Activations Density 0.281%

    No Known Activations