© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8621
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly those associated with prominent individuals named Bill

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

    "Bill" or "William" followed by a last name

    np_acts-logits-general · gemini-2.0-flash

    bill followed by surname

    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
     BorderRadius
    -0.77
    masing
    -0.66
    Viited
    -0.66
    XmlAccessType
    -0.61
     InputDecoration
    -0.60
    ITECH
    -0.54
    redited
    -0.53
    BeginInit
    -0.53
     thuộc
    -0.53
    ponses
    -0.53
    POSITIVE LOGITS
     Bill
    1.05
     Bills
    1.03
     bill
    1.01
     BILL
    1.00
     bills
    0.99
    Bill
    0.96
    BILL
    0.95
    Bills
    0.93
    bill
    0.85
     invoice
    0.73
    Activations Density 0.122%

    No Known Activations