Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53298
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Morgan."

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

    Morgan and associated proper nouns

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    verwijspagina
    -0.99
    FormTagHelper
    -0.92
     NSCoder
    -0.88
     démocr
    -0.88
     betweenstory
    -0.84
    CreateMap
    -0.84
     aéri
    -0.84
     Widodo
    -0.84
    Personensuche
    -0.84
    GEBURTS
    -0.83
    POSITIVE LOGITS
     Morgan
    0.85
    ally
    0.66
    Morgan
    0.63
    o
    0.59
    ite
    0.57
    elt
    0.57
    ville
    0.54
    ized
    0.54
    a
    0.52
     M
    0.52
    Activations Density 0.030%

    No Known Activations