© 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. 16-GEMMASCOPE-RES-16K
    11. 5916
    Prev
    Next
    INDEX
    Explanations

    phrases that express sorts or kinds of things

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

    approximation ("kinda", "sorta", "rather")

    np_acts-logits-general · gemini-2.0-flash

    qualifiers like kinda or somewhat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     armées
    -0.53
     hectáreas
    -0.52
     bague
    -0.51
     puissante
    -0.50
     édition
    -0.49
     hlad
    -0.49
    USART
    -0.49
    Surviving
    -0.48
     céramique
    -0.48
     municipale
    -0.48
    POSITIVE LOGITS
     sorta
    0.94
    Kinda
    0.83
     Kinda
    0.77
    kinda
    0.73
     kinda
    0.72
    GroupLayout
    0.70
     like
    0.69
     unknownFields
    0.68
     trampa
    0.65
    Somewhat
    0.64
    Activations Density 0.135%

    No Known Activations