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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6570
    Prev
    Next
    INDEX
    Explanations

    phrases related to shipping offers and promotions

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

    Follows offers like "delivery" or "available."

    np_acts-logits-general · gemini-2.0-flash

    delivery, location, or availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     far
    -0.48
     Lend
    -0.47
    owy
    -0.44
    Cornell
    -0.43
    Spoljašnje
    -0.42
     استنادى
    -0.41
     cotone
    -0.41
     Staates
    -0.39
    pren
    -0.38
    utt
    -0.38
    POSITIVE LOGITS
     desertcart
    1.05
    aarrggbb
    1.00
     nahilalakip
    0.90
     ModelExpression
    0.88
     يتيمه
    0.84
    desertcart
    0.83
     للمعارف
    0.82
     disambiguazione
    0.79
     चीज़ों
    0.78
     дописавши
    0.75
    Activations Density 0.024%

    No Known Activations