© 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. 5612
    Prev
    Next
    INDEX
    Explanations

    various forms of hierarchy and significance within relationships or roles mentioned in the text

    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
    complexContent
    -0.42
    ombus
    -0.41
    kmäler
    -0.36
    anthene
    -0.36
    SafeMath
    -0.35
    HasIndex
    -0.35
    momix
    -0.35
     MainAxisSize
    -0.35
     ffilmiau
    -0.34
    loroethene
    -0.34
    POSITIVE LOGITS
     cap
    3.44
     Cap
    3.36
    Cap
    3.31
    cap
    3.16
     CAP
    2.83
     kap
    2.81
     caps
    2.72
    CAP
    2.70
     Kap
    2.66
    Kap
    2.64
    Activations Density 1.093%

    No Known Activations