© 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. 30-GEMMASCOPE-RES-16K
    11. 12410
    Prev
    Next
    INDEX
    Explanations

    mentions of food-related items and establishments

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

    Follows verbs "do," "is," or "seem."

    np_acts-logits-general · gemini-2.0-flash

    offers and offerings

    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
     aprend
    -0.37
     escapar
    -0.36
     learn
    -0.34
     zakup
    -0.34
     drawn
    -0.33
     enjoy
    -0.33
     Enjoy
    -0.32
    исленность
    -0.32
    Personendaten
    -0.32
     Eink
    -0.31
    POSITIVE LOGITS
     offers
    1.02
     offering
    0.98
    offers
    0.94
     menawarkan
    0.94
     offer
    0.92
    offering
    0.91
    Offers
    0.86
     tilby
    0.85
     erbjuder
    0.85
     предлагает
    0.83
    Activations Density 0.424%

    No Known Activations