© 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. 1350
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases or structures related to the occurrence of the word "once"

    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
     Geno
    -0.61
    変わり
    -0.60
    otus
    -0.60
     Кі
    -0.59
    imath
    -0.58
    tory
    -0.58
    /**
    -0.57
     готовы
    -0.56
    craft
    -0.56
     meda
    -0.56
    POSITIVE LOGITS
     once
    3.02
    once
    2.80
    Once
    2.55
     ONCE
    2.55
     Once
    2.51
    ONCE
    2.30
     einmal
    1.35
     egyszer
    1.29
    一度
    1.25
     مرة
    1.22
    Activations Density 0.028%

    No Known Activations