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

    Neuronpedia

    APICircuit 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2225
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Nas" and its variations, indicating a focus on individuals or references to specific figures associated with the name "Nas."

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

    "Nas" followed by a single letter

    np_acts-logits-general · gemini-2.0-flash

    Names like Nasr and Nat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    롭
    -0.55
     Varela
    -0.52
     Farina
    -0.51
     Verenigde
    -0.49
    addGap
    -0.47
    quee
    -0.47
    phosa
    -0.45
    weza
    -0.45
    ńskim
    -0.45
     Vertrauen
    -0.45
    POSITIVE LOGITS
     kaarangay
    0.66
    runApp
    0.64
    ագրություններ
    0.63
    Referencies
    0.62
     AssemblyCulture
    0.62
    QMetaType
    0.61
    MessageOf
    0.59
    tadır
    0.57
     NSCoder
    0.56
    цездатний
    0.56
    Activations Density 0.130%

    No Known Activations