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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12146
    Prev
    Next
    INDEX
    Explanations

    mentions of meetings or formal gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    liferay
    -0.44
    assertions
    -0.40
    buh
    -0.40
    riera
    -0.39
    dflare
    -0.38
    prá
    -0.37
    нах
    -0.36
     './
    -0.36
    fante
    -0.36
     /\.(
    -0.34
    POSITIVE LOGITS
     meeting
    1.71
     meetings
    1.63
    meeting
    1.59
    Meeting
    1.54
     Meeting
    1.51
    Meetings
    1.44
     Meetings
    1.43
    meetings
    1.42
     MEETING
    1.36
     session
    1.25
    Activations Density 0.323%

    No Known Activations