© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106925
    Prev
    Next
    INDEX
    Explanations

    instances of the word "genuine" or its variations, indicating a focus on authenticity

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

    genuine abstract nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    enumi
    -0.55
     Houſe
    -0.53
     Batam
    -0.53
     list
    -0.49
     bombing
    -0.49
    колай
    -0.49
    IRP
    -0.49
     nanny
    -0.49
     Lancelot
    -0.48
    setList
    -0.48
    POSITIVE LOGITS
    genuine
    1.00
    Genuine
    0.96
     genuine
    0.95
     Genuine
    0.94
    enuine
    0.93
    genu
    0.88
     Genu
    0.86
     genuinely
    0.83
     genu
    0.72
     Honest
    0.66
    Activations Density 0.006%

    No Known Activations