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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15409
    Prev
    Next
    INDEX
    Explanations

    terms related to offers or proposals in various contexts

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

    "offer" or "offering"

    np_acts-logits-general · gemini-2.0-flash

    offer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ReactDOM
    -0.39
     bande
    -0.38
     vio
    -0.38
    currentNode
    -0.37
     Walton
    -0.36
    LEncoder
    -0.36
     Vio
    -0.35
     bVar
    -0.35
    asteel
    -0.35
     Burgos
    -0.34
    POSITIVE LOGITS
     Offer
    0.83
    oredCriteria
    0.70
    Offer
    0.69
    offer
    0.69
    offers
    0.64
     OFFER
    0.61
     offer
    0.60
     Offers
    0.59
     snippetHide
    0.58
     שוליים
    0.56
    Activations Density 0.074%

    No Known Activations