© 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. 5658
    Prev
    Next
    INDEX
    Explanations

    key terms related to medical and health-related topics, particularly in the context of surgery and public health issues

    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
     approximately
    -0.57
     aproximadamente
    -0.57
    hereinafter
    -0.55
     daquele
    -0.55
     hereinafter
    -0.52
     subsequently
    -0.52
     natomiast
    -0.51
    いわゆる
    -0.51
     непосредственно
    -0.49
     ungefähr
    -0.49
    POSITIVE LOGITS
     govt
    0.96
     ‘
    0.94
     '
    0.85
     Govt
    0.84
    govt
    0.82
    Govt
    0.79
     Dems
    0.76
     nuke
    0.75
     NYC
    0.74
     gov
    0.74
    Activations Density 0.420%

    No Known Activations