© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2968
    Prev
    Next
    INDEX
    Explanations

    the prefix "re" indicating repetition or reoccurrence in various contexts

    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
     Theſe
    -0.85
    LayoutStyle
    -0.73
     Wikispecies
    -0.71
     sappi
    -0.70
    Artículos
    -0.69
    BeginContext
    -0.69
     Beſ
    -0.67
    etheless
    -0.67
     iſt
    -0.66
     ་་
    -0.66
    POSITIVE LOGITS
     re
    3.04
    Re
    2.19
     Re
    2.16
     RE
    1.83
    re
    1.69
    RE
    1.52
    重新
    1.39
     재
    1.33
     ré
    1.29
     Rea
    1.26
    Activations Density 0.078%

    No Known Activations