© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 74806
    Prev
    Next
    INDEX
    Explanations

    phrases that use the word "quite" to emphasize a degree of intensity or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "quite" followed by a descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DRS
    -0.52
    LocationManager
    -0.47
     return
    -0.45
     atras
    -0.45
     DRS
    -0.45
    PRP
    -0.44
     Cardona
    -0.43
    return
    -0.42
     tronco
    -0.40
    SSP
    -0.39
    POSITIVE LOGITS
     quite
    0.91
    Quite
    0.84
     very
    0.82
     Quite
    0.82
     pretty
    0.80
    quite
    0.77
    astanza
    0.76
     nice
    0.75
    pretty
    0.74
     fairly
    0.70
    Activations Density 0.007%

    No Known Activations