© 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. 36-GEMMASCOPE-RES-16K
    11. 7561
    Prev
    Next
    INDEX
    Explanations

    terms associated with blood transfusions and immune responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jelder
    -0.39
    cox
    -0.37
    Brent
    -0.35
    อิง
    -0.35
     IFTT
    -0.35
    vex
    -0.35
    şiv
    -0.35
    沐
    -0.35
     onPage
    -0.35
    AnimationsModule
    -0.35
    POSITIVE LOGITS
     hemoglobin
    1.03
     RBC
    0.95
     Hem
    0.90
     erythrocytes
    0.89
     hem
    0.88
     haem
    0.87
     anemia
    0.87
    RBC
    0.84
     red
    0.81
     hemo
    0.80
    Activations Density 1.093%

    No Known Activations