© 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. 119933
    Prev
    Next
    INDEX
    Explanations

    references to historical events related to the atomic bombings of Hiroshima and Nagasaki

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     amores
    -0.37
    unehmen
    -0.36
     cuidado
    -0.31
     jeito
    -0.31
     novios
    -0.31
     povr
    -0.30
     ajan
    -0.30
     shapes
    -0.29
     ne
    -0.29
     livery
    -0.29
    POSITIVE LOGITS
     faſt
    0.92
     ſever
    0.85
     deſt
    0.83
     ſte
    0.78
    enterOuterAlt
    0.77
    ſelf
    0.77
    AsUp
    0.76
     diſt
    0.75
     ſta
    0.75
     leaſt
    0.74
    Activations Density 0.018%

    No Known Activations