© 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. 15968
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to measurements and calculations in scientific contexts

    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
     AssemblyCulture
    -0.63
    tagHelperRunner
    -0.60
     autorytatywna
    -0.59
    DIPSETTING
    -0.55
    RenderAtEndOf
    -0.54
    锈钢
    -0.54
    enterOuterAlt
    -0.51
     transfieras
    -0.51
     intptr
    -0.51
    енча
    -0.50
    POSITIVE LOGITS
     efficiently
    1.91
     correctly
    1.91
     properly
    1.77
     nicely
    1.74
     adequately
    1.73
     accurately
    1.73
     excellently
    1.70
     flawlessly
    1.69
     perfectly
    1.68
     effectively
    1.66
    Activations Density 3.061%

    No Known Activations