© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 3813
    Prev
    Next
    INDEX
    Explanations

    the repetition 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 @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 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
    saraba
    -0.58
    uttori
    -0.54
     Chwiliwch
    -0.54
    réhen
    -0.53
    bsd
    -0.52
    aspectj
    -0.51
     rechange
    -0.51
     forbear
    -0.50
    спонд
    -0.50
    ktor
    -0.50
    POSITIVE LOGITS
     once
    4.75
    once
    4.37
    Once
    4.33
     Once
    4.29
     ONCE
    3.91
    ONCE
    3.66
     einmal
    2.19
    一旦
    2.10
    一度
    1.86
     مرة
    1.78
    Activations Density 0.054%

    No Known Activations