© 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. 15772
    Prev
    Next
    INDEX
    Explanations

    specific categories or classifications within various 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
     milliers
    -0.66
     centaines
    -0.61
     jScrollPane
    -0.59
     tartalomajánló
    -0.58
     Wiktionnaire
    -0.57
     berbagai
    -0.56
     birçok
    -0.56
     segala
    -0.56
     pelbagai
    -0.54
     vieler
    -0.54
    POSITIVE LOGITS
     namely
    1.07
     apiece
    1.05
    分别是
    0.95
     plus
    0.94
     totaling
    0.92
     consecutively
    0.90
     totalling
    0.90
    分別
    0.90
     respectively
    0.85
     consecu
    0.82
    Activations Density 1.104%

    No Known Activations