© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103988
    Prev
    Next
    INDEX
    Explanations

    names and references related to conspiracies and allegations involving significant historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    UnusedPrivate
    -0.49
    ternut
    -0.45
    matchCondition
    -0.41
     assoluto
    -0.39
     للمعارف
    -0.39
     lusso
    -0.39
    綢
    -0.38
     bellezza
    -0.38
    dolu
    -0.38
    kusen
    -0.38
    POSITIVE LOGITS
    //
    0.57
     conspiracy
    0.57
     mysterious
    0.53
     <>",
    0.47
     mysteriously
    0.47
    謎
    0.47
     conspira
    0.47
     mystery
    0.44
     myster
    0.44
     astore
    0.43
    Activations Density 0.148%

    No Known Activations