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. 16-GEMMASCOPE-RES-16K
    6. 15689
    Prev
    Next
    INDEX
    Explanations

    phrases and terms associated with the transaction or exchange of properties or assets

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

    Follows "the", preposition, or conjunction

    np_acts-logits-general · gemini-2.0-flash

    potential sale, interested buyers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.74
     Shakspeare
    -0.64
     utafitiHapana
    -0.63
     Sopho
    -0.62
    Demografie
    -0.61
    بوابة
    -0.61
    PageFactory
    -0.61
    Portale
    -0.59
    LayoutConstraint
    -0.58
    __(/*!
    -0.57
    POSITIVE LOGITS
     buyers
    1.01
     purchasers
    0.94
     buyer
    0.83
     interested
    0.82
     purchaser
    0.77
     Buyers
    0.74
    buyers
    0.72
     acheteurs
    0.72
    Buyers
    0.69
    interested
    0.68
    Activations Density 0.382%

    No Known Activations