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

    Neuronpedia

    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. 5610
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports contracts and player transitions

    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
    تقاوى
    -0.86
     ProtoMessage
    -0.86
     ویکی‌پدی
    -0.85
    contentLoaded
    -0.84
     betweenstory
    -0.81
    RenderAtEndOf
    -0.80
    tagHelperRunner
    -0.79
    Personendaten
    -0.79
     kasarigan
    -0.78
     ddelweddau
    -0.77
    POSITIVE LOGITS
     hombros
    0.63
     posteriores
    0.63
     épaules
    0.62
     later
    0.56
     rodillas
    0.55
     vė
    0.54
     oscuros
    0.53
     thereafter
    0.52
     pozdě
    0.51
     varones
    0.49
    Activations Density 1.089%

    No Known Activations