© 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. 20-GEMMASCOPE-RES-16K
    11. 4376
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation

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

    Gratitude expressed with "thanks."

    np_acts-logits-general · gemini-2.0-flash

    thanks and gratitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    fillType
    -0.79
     esternos
    -0.72
     onPage
    -0.70
     wireType
    -0.68
    __((
    -0.67
    routeProvider
    -0.66
    iNdEx
    -0.64
    IBOutlet
    -0.61
    WriteTagHelper
    -0.58
    ApiModel
    -0.58
    POSITIVE LOGITS
     thanks
    0.90
    Thanks
    0.84
     goodness
    0.84
     Thanks
    0.83
     THANKS
    0.81
     heavens
    0.77
     graças
    0.77
    thanks
    0.76
     gracias
    0.75
     god
    0.74
    Activations Density 0.035%

    No Known Activations