© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5516
    Prev
    Next
    INDEX
    Explanations

    the word "stay" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    subequations
    -0.47
     otomatig
    -0.44
     Gnade
    -0.44
    Adorable
    -0.43
     Dutton
    -0.42
    ="../../
    -0.42
     regalías
    -0.41
     Seamless
    -0.40
     Edelman
    -0.40
    ítez
    -0.39
    POSITIVE LOGITS
     stay
    1.01
    stay
    0.94
    Stay
    0.93
     Stay
    0.92
    STAY
    0.88
     STAY
    0.81
     stays
    0.80
     island
    0.73
    stays
    0.71
     Staying
    0.70
    Activations Density 0.050%

    No Known Activations