© 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. 4281
    Prev
    Next
    INDEX
    Explanations

    elements related to software programming and data management

    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
    IRQn
    -0.35
     StatelessWidget
    -0.30
     too
    -0.30
     clássico
    -0.29
     Wikimedijinoj
    -0.28
     anlaş
    -0.28
    之色
    -0.28
    ніципалі
    -0.28
     gestorben
    -0.28
     fondly
    -0.27
    POSITIVE LOGITS
     manager
    0.79
     dispatcher
    0.70
    管理器
    0.69
     engine
    0.68
     session
    0.66
     context
    0.64
     mgr
    0.64
    ScopeManager
    0.62
     environment
    0.61
     logger
    0.61
    Activations Density 0.699%

    No Known Activations