Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 16243
    Prev
    Next
    INDEX
    Explanations

    phrases related to introductions and formal communication protocols

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

    Followed by "meet" or related words

    np_acts-logits-general · gemini-2.0-flash

    introductions and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irical
    -0.54
    Архівовано
    -0.53
    CDATA
    -0.52
    ыгана
    -0.51
     resourceCulture
    -0.51
    Filtering
    -0.50
    diva
    -0.49
    curacies
    -0.49
    UserScript
    -0.49
     pfe
    -0.48
    POSITIVE LOGITS
     meet
    2.92
     meeting
    2.76
     Meet
    2.63
    meet
    2.58
     met
    2.56
    Meet
    2.53
     meets
    2.52
    Meeting
    2.45
     MEET
    2.37
     Meeting
    2.36
    Activations Density 0.264%

    No Known Activations