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

    Neuronpedia

    Jacobian LensNEW
    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. 30-GEMMASCOPE-RES-16K
    11. 9655
    Prev
    Next
    INDEX
    Explanations

    specific names of companies or organizations involved in business transactions

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

    Car dealerships and representations

    np_acts-logits-general · gemini-2.0-flash

    dealerships and car representations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GeneratedMessage
    -0.46
     alkot
    -0.44
    dflare
    -0.43
    
    -0.42
    عرِّف
    -0.42
     inscrição
    -0.41
    anggap
    -0.41
    cetamol
    -0.40
    ensore
    -0.40
     चीज़ों
    -0.40
    POSITIVE LOGITS
     dealership
    1.38
     dealer
    1.30
     dealerships
    1.27
     dealers
    1.16
     Dealer
    1.14
    dealer
    1.11
     Dealers
    1.09
    Dealer
    1.05
     showroom
    0.97
    Deal
    0.96
    Activations Density 0.179%

    No Known Activations