© 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. 8603
    Prev
    Next
    INDEX
    Explanations

    programming code structures and syntax 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
    Exo
    -0.62
     Эк
    -0.61
    Ex
    -0.61
    Enc
    -0.60
    EX
    -0.59
    ELE
    -0.59
     Ex
    -0.58
    Eff
    -0.56
     Exo
    -0.56
    EXP
    -0.56
    POSITIVE LOGITS
    épaisseur
    0.94
     е
    0.91
     e
    0.90
    enfance
    0.83
    échelle
    0.79
    écart
    0.75
     é
    0.69
    hygiène
    0.68
    entraînement
    0.68
    humanité
    0.67
    Activations Density 1.344%

    No Known Activations