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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53108
    Prev
    Next
    INDEX
    Explanations

    expressions of inclusivity or collective experience

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

    return, prefer, like, whatever, all

    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
     DriverManager
    -0.60
     Оно
    -0.48
    <thead>
    -0.45
    <>
    
    -0.44
    SequentialGroup
    -0.44
    ═
    -0.43
    └──
    -0.42
    BorderFactory
    -0.42
    [
    
    -0.42
    chim
    -0.41
    POSITIVE LOGITS
    OGND
    0.79
     lenker
    0.68
     transférez
    0.62
    وعة
    0.58
    Билгалдахарш
    0.58
    WithMany
    0.56
    AndEndTag
    0.55
    TemporalType
    0.54
    webElementXpaths
    0.54
    Fns
    0.53
    Activations Density 0.382%

    No Known Activations