© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 63772
    Prev
    Next
    INDEX
    Explanations

    specific terms related to risk factors and their implications in various medical contexts

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

    factors and reasons

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects mentions of "risk/factors" and related study language (e.g., predictors, associated, identify) indicating risk factors or factors in research contexts.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    phrases in scientific or technical texts that discuss factors or predictors (especially risk factors) and related study aims or analysis details.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.48
    uarts
    -0.47
     Italijani
    -0.46
    WireFormatLite
    -0.45
    الحياه
    -0.43
    GIVEREF
    -0.43
    MLLoader
    -0.43
    ToolStrip
    -0.42
     Taktlose
    -0.42
    contra
    -0.42
    POSITIVE LOGITS
     factors
    0.76
     Factors
    0.71
    Factors
    0.66
    factors
    0.63
     reasons
    0.57
     factores
    0.57
     FACTORS
    0.56
     Reasons
    0.54
    Reasons
    0.54
     Gründe
    0.51
    Activations Density 0.442%

    No Known Activations