© 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. 19-GEMMASCOPE-RES-16K
    11. 3780
    Prev
    Next
    INDEX
    Explanations

    instances of the word "keep" and its variations, particularly in contexts that suggest maintenance or preservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ----</
    -0.74
     kasarigan
    -0.73
    
    -0.72
    ⓧ
    -0.71
     disponibilités
    -0.70
     مشين
    -0.70
    bootstrapcdn
    -0.70
     initComponents
    -0.69
     setuptools
    -0.68
    convenience
    -0.66
    POSITIVE LOGITS
     alive
    1.11
     afloat
    0.83
     intact
    0.80
    alive
    0.75
     keep
    0.68
     kept
    0.68
     stay
    0.66
     Alive
    0.64
     away
    0.64
     abreast
    0.62
    Activations Density 0.150%

    No Known Activations