© 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. 8530
    Prev
    Next
    INDEX
    Explanations

    code constructs and operations related to sorting and managing data structures

    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
    UnusedPrivate
    -0.57
    enderror
    -0.46
     informée
    -0.44
    Erreferentziak
    -0.44
     ouverts
    -0.41
    Ārējās
    -0.40
    PreInfinity
    -0.40
     forfeiture
    -0.40
    httphttps
    -0.39
     éto
    -0.39
    POSITIVE LOGITS
     sorting
    1.77
     sorted
    1.70
     sort
    1.55
     Sort
    1.55
     Sorting
    1.54
    sort
    1.54
    Sort
    1.52
     SORT
    1.45
    排序
    1.41
    Sorting
    1.41
    Activations Density 0.563%

    No Known Activations