© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 7729
    Prev
    Next
    INDEX
    Explanations

    specifics about cytokines and their interactions in cellular responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بوابة
    -0.90
    CELLANEOUS
    -0.73
     Cuenca
    -0.72
     clim
    -0.71
     inqui
    -0.69
     ")");
    -0.69
     CPE
    -0.69
     Karel
    -0.66
     Marguerite
    -0.66
     Cabe
    -0.66
    POSITIVE LOGITS
     IL
    2.38
     Il
    2.20
    Il
    1.89
     il
    1.83
    IL
    1.75
     İl
    1.24
    il
    1.24
     Illinois
    1.01
    leukin
    1.01
     Ili
    1.01
    Activations Density 0.087%

    No Known Activations