© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 790
    Prev
    Next
    INDEX
    Explanations

    instances of the word "meet" and its variations, indicating discussions or gatherings

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

    "meet" or "meeting"

    np_acts-logits-general · gemini-2.0-flash

    meeting

    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
    ViewFeatures
    -0.79
    estacks
    -0.79
    жалуйста
    -0.77
    }{*}{
    -0.75
    ArgsConstructor
    -0.73
    DataAnnotations
    -0.73
     насељу
    -0.71
    nodoc
    -0.71
    BagLayout
    -0.71
    $_['
    -0.70
    POSITIVE LOGITS
     MEET
    1.07
    MEET
    0.94
     meet
    0.93
     meets
    0.92
    meet
    0.91
    Meet
    0.89
     met
    0.88
     Meet
    0.87
    Meetings
    0.87
     Meetings
    0.86
    Activations Density 0.078%

    No Known Activations