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. 11-GEMMASCOPE-RES-16K
    6. 5878
    Prev
    Next
    INDEX
    Explanations

    specific quantitative or comparative evaluations of conditions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.56
     krop
    -0.54
     musique
    -0.47
    ьера
    -0.46
     reversible
    -0.46
     sạn
    -0.45
     trần
    -0.45
    gemäß
    -0.45
    ucks
    -0.45
    免费
    -0.44
    POSITIVE LOGITS
    windowFixed
    0.84
    AsUp
    0.78
    RegressionTest
    0.75
    EDEFAULT
    0.72
     GetEnumerator
    0.71
    StoreMessageInfo
    0.69
    Personensuche
    0.68
    PerformLayout
    0.68
     otomatig
    0.64
     препратки
    0.63
    Activations Density 1.257%

    No Known Activations