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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 40732
    Prev
    Next
    INDEX
    Explanations

    text related to email management and productivity features

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

    References to email inboxes, communication systems, and productivity features. Often mentions specific email clients (Gmail, Outlook), inbox organization, filtering based on contacts/important people, and office/work communication concepts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    featureID
    -0.39
    UrlResolution
    -0.36
     eğ
    -0.35
     auszu
    -0.35
    距
    -0.33
    
    -0.33
    (&_
    -0.33
    RefNanny
    -0.32
     disfrute
    -0.32
     diversión
    -0.32
    POSITIVE LOGITS
     office
    0.58
    OFFICE
    0.57
     secretaries
    0.55
    office
    0.55
    secretary
    0.54
     secretary
    0.54
    meetings
    0.53
    desk
    0.52
    Desk
    0.51
    Gmail
    0.51
    Activations Density 0.067%

    No Known Activations