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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 175
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of deals and agreements

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

    the word "deal" in various contexts, particularly in business, finance, or negotiation scenarios.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     Northumberland
    -0.60
     Whitby
    -0.60
     Northwest
    -0.56
    Northwest
    -0.56
     Minerva
    -0.56
     Савезне
    -0.55
     Sandberg
    -0.54
     humanist
    -0.54
     Maurice
    -0.53
     McMaster
    -0.53
    POSITIVE LOGITS
     Deal
    1.23
     deal
    1.22
    deal
    1.20
    Deal
    1.19
     DEAL
    1.10
     Deals
    1.03
     deals
    1.01
    deals
    0.96
    DEAL
    0.93
     dealt
    0.92
    Activations Density 0.048%

    No Known Activations