© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15331
    Prev
    Next
    INDEX
    Explanations

    references to cytokines and related biological terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Cy" followed by other characters/digits

    np_acts-logits-general · gemini-2.0-flash

    words starting with cy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.59
     Moffat
    -0.57
    GRANTED
    -0.56
    Parameteri
    -0.55
    remadura
    -0.55
    //}
    -0.55
    كومة
    -0.53
     lượt
    -0.52
    endregion
    -0.52
     atlik
    -0.52
    POSITIVE LOGITS
     cy
    1.02
     Cy
    0.97
     CY
    0.94
     Cyc
    0.85
    Cycles
    0.83
    Cy
    0.82
     cycles
    0.80
    cy
    0.79
    Ciclo
    0.78
     Cycles
    0.78
    Activations Density 0.172%

    No Known Activations