© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 6735
    Prev
    Next
    INDEX
    Explanations

    references to puzzles and passive interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Histórico
    -0.38
     betrek
    -0.36
     liggen
    -0.36
     gekomen
    -0.35
     strijd
    -0.35
     igjen
    -0.34
    Exodus
    -0.34
     épaules
    -0.34
     histórico
    -0.34
     nedenle
    -0.34
    POSITIVE LOGITS
     blind
    0.90
     EconPapers
    0.84
     homeless
    0.83
    blind
    0.80
     drones
    0.80
     passive
    0.77
     Blind
    0.76
     idiot
    0.76
     puzzle
    0.75
     drone
    0.73
    Activations Density 0.416%

    No Known Activations