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. 3203
    Prev
    Next
    INDEX
    Explanations

    terms related to "trans-" prefix words or processes

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

    starting with "trans"

    np_acts-logits-general · gemini-2.0-flash

    translation, transit, transplant, transmittance, transverse, transformed

    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
    Климат
    -0.68
    EDEFAULT
    -0.64
    MeasureSpec
    -0.57
    metheus
    -0.54
    rinfo
    -0.54
    Демографія
    -0.53
    checs
    -0.52
    BeforeClass
    -0.52
     '\\;'
    -0.51
     protoimpl
    -0.51
    POSITIVE LOGITS
     transf
    0.62
    alist
    0.60
     الاطلاع
    0.60
    AutoresizingMask
    0.60
    ations
    0.58
    Билгалдахарш
    0.58
    ally
    0.57
    脚注の使い方
    0.57
     poveznice
    0.57
    ational
    0.56
    Activations Density 0.182%

    No Known Activations