© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 122
    Prev
    Next
    INDEX
    Explanations

    references to air and its related qualities or conditions

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

    references to air-related topics and systems

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

    air pollution and conditioning

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    expandindo
    -0.90
    NameInMap
    -0.70
    IndentedString
    -0.69
    docx
    -0.68
     تضيفلها
    -0.67
    __);
    -0.67
    naires
    -0.66
    älter
    -0.65
    ())),
    -0.65
    prägt
    -0.63
    POSITIVE LOGITS
     conditioning
    0.72
     AIR
    0.65
    conditioning
    0.63
    waves
    0.61
    pertino
    0.57
     Luft
    0.56
     Airs
    0.56
     air
    0.55
    AIR
    0.55
    니다
    0.55
    Activations Density 0.035%

    No Known Activations