© 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. 4698
    Prev
    Next
    INDEX
    Explanations

    components related to recreational and wellness activities

    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
     ExecuteAsync
    -0.56
     Blackboard
    -0.39
     Netanyahu
    -0.39
    GOTREF
    -0.39
    queiro
    -0.38
     للاسماء
    -0.38
    :+:
    -0.38
     Tallahassee
    -0.37
     giao
    -0.37
    MethodManager
    -0.36
    POSITIVE LOGITS
     bath
    2.00
     baths
    1.79
     Bath
    1.63
    bath
    1.59
    Bath
    1.55
     bathing
    1.54
     BATH
    1.50
     Baths
    1.49
     bathe
    1.46
     shower
    1.43
    Activations Density 0.149%

    No Known Activations