© 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. 9366
    Prev
    Next
    INDEX
    Explanations

    repeated references to the word "same" 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
     propOrder
    -0.74
    ardı
    -0.70
     découvrez
    -0.68
    ıldız
    -0.67
    déric
    -0.66
     BoxDecoration
    -0.65
    setupUi
    -0.64
     commerciales
    -0.63
    modb
    -0.63
    nani
    -0.63
    POSITIVE LOGITS
     same
    2.87
    same
    2.70
    Same
    2.64
     Same
    2.44
    SAME
    2.36
     SAME
    2.35
     samme
    1.82
     samma
    1.80
     mesma
    1.78
     dezelfde
    1.77
    Activations Density 0.067%

    No Known Activations