© 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. 12-GEMMASCOPE-RES-16K
    11. 2304
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stay" and its variations, indicating a focus on permanence or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ็ต
    -0.69
     Richmond
    -0.68
     ello
    -0.68
     zod
    -0.68
     éc
    -0.66
     Dickerson
    -0.66
    Richmond
    -0.66
    icos
    -0.66
    "])){
    -0.65
    ]))
    -0.65
    POSITIVE LOGITS
    stay
    1.57
     stay
    1.54
    STAY
    1.48
     Stay
    1.42
    Stay
    1.41
     STAY
    1.38
     Staying
    1.32
     stays
    1.29
     staying
    1.25
     stayed
    1.24
    Activations Density 0.097%

    No Known Activations