© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13923
    Prev
    Next
    INDEX
    Explanations

    instances of the word "meet" and related variations indicating meetings or appointments

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

    "meet" and its variations

    np_acts-logits-general · gemini-2.0-flash

    meeting people or with others

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    AsString
    -0.45
     aikaa
    -0.43
    StringProperty
    -0.43
    //
    -0.42
     zand
    -0.41
    bellar
    -0.41
     Northwestern
    -0.41
    WebElementEntity
    -0.41
    ariatric
    -0.39
    ⁾
    -0.39
    POSITIVE LOGITS
    Meet
    1.23
    meet
    1.21
     meet
    1.20
    Meeting
    1.19
     Meet
    1.18
     MEET
    1.13
     Meeting
    1.13
     meeting
    1.13
    meeting
    1.13
     meets
    1.05
    Activations Density 0.075%

    No Known Activations