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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 11676
    Prev
    Next
    INDEX
    Explanations

    references to improvement and change over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gioielli
    -0.54
     geweest
    -0.53
     ویکی‌پدیا
    -0.45
     rimasto
    -0.44
     sogno
    -0.43
    一直
    -0.43
     étoit
    -0.43
     Wird
    -0.42
    devamını
    -0.42
     Schlüssel
    -0.42
    POSITIVE LOGITS
    ValueStyle
    0.77
     hơn
    0.67
    webElementXpaths
    0.67
    Geplaatst
    0.67
    ContextHolder
    0.66
     now
    0.63
    principalTable
    0.63
    QMetaType
    0.62
     sweeter
    0.61
    帖最后由
    0.60
    Activations Density 0.362%

    No Known Activations