© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15999
    Prev
    Next
    INDEX
    Explanations

    intensifying adverbs, particularly "quite."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     culturelles
    -0.81
    بوابة
    -0.67
    ://
    -0.66
     Krueger
    -0.66
     Kearney
    -0.65
    Bermuda
    -0.65
    SWG
    -0.63
     Flanagan
    -0.62
     Magdeburg
    -0.61
    dora
    -0.60
    POSITIVE LOGITS
     quite
    1.12
    quite
    1.09
     Quite
    0.94
    Quite
    0.91
    uttosto
    0.88
    ParallelGroup
    0.86
     Audiodateien
    0.83
     alright
    0.81
    Interess
    0.80
    ukup
    0.78
    Activations Density 0.011%

    No Known Activations