© 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. 37-GEMMASCOPE-RES-16K
    11. 4575
    Prev
    Next
    INDEX
    Explanations

    expressions and operations related to mathematical or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rhestr
    -0.40
     disponibilités
    -0.36
    которые
    -0.33
     raste
    -0.32
    protoc
    -0.32
    いき
    -0.31
     кре
    -0.30
    WebControls
    -0.30
     تضيفلها
    -0.29
    ories
    -0.29
    POSITIVE LOGITS
    页面存档备份
    0.94
    uxxxx
    0.81
    bibfield
    0.78
    findpost
    0.73
    BibitemShut
    0.71
    bibinfo
    0.64
    ScopeManager
    0.60
     okuyayım
    0.59
     zelve
    0.58
    出版年
    0.57
    Activations Density 1.624%

    No Known Activations