© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7404
    Prev
    Next
    INDEX
    Explanations

    key terms related to distributors and distribution in sales and marketing contexts

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

    business and commercial transaction language, particularly involving distribution, sales, and supply chain terms.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    business relationships involving distribution, sales, or supply of products and services.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of business distribution and sales channels, such as appointing distributors, wholesale/reseller relationships, and import/export arrangements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    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
    jména
    -0.43
    archiviato
    -0.42
     valoración
    -0.39
     Règlement
    -0.39
    odios
    -0.38
    Captor
    -0.37
     Biaya
    -0.36
    AtIndexPath
    -0.36
    wendungen
    -0.35
    ipu
    -0.35
    POSITIVE LOGITS
     distributors
    1.88
     distributor
    1.88
     distribution
    1.78
     distribut
    1.72
     Distributor
    1.68
     distribu
    1.65
     Distribution
    1.64
     distribute
    1.61
     Distributors
    1.59
     distributing
    1.58
    Activations Density 0.252%

    No Known Activations