© 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. 5620
    Prev
    Next
    INDEX
    Explanations

    medical terminologies related to treatments and therapies

    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
    quido
    -0.33
     Fieber
    -0.31
     camisa
    -0.31
    雑
    -0.31
     felé
    -0.30
    Géographie
    -0.30
     Badge
    -0.29
     Kulit
    -0.28
     merak
    -0.28
    覓
    -0.28
    POSITIVE LOGITS
     therapy
    1.48
     therapies
    1.45
     treatment
    1.40
     treatments
    1.27
     Therapy
    1.18
     Therapies
    1.18
     terapi
    1.14
    therapy
    1.13
    treatment
    1.13
     Treatment
    1.13
    Activations Density 1.876%

    No Known Activations