© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1681
    Prev
    Next
    INDEX
    Explanations

    the word "once" and its variations, indicating repetitions or conditions of occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.68
     understatement
    -0.61
    saraba
    -0.61
    maline
    -0.59
    lastic
    -0.57
    kungen
    -0.57
    pacho
    -0.55
    ლი
    -0.54
     gradova
    -0.53
    membrance
    -0.53
    POSITIVE LOGITS
    Once
    1.84
     Once
    1.83
     once
    1.65
     ONCE
    1.57
    once
    1.55
    ONCE
    1.54
     Sobald
    1.02
     einmal
    0.95
     sobald
    0.87
     vez
    0.83
    Activations Density 0.205%

    No Known Activations