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. 5-GEMMASCOPE-RES-16K
    6. 2079
    Prev
    Next
    INDEX
    Explanations

    phrases that denote conclusions or final statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیا
    -0.88
    ViewImports
    -0.83
     Baillargeon
    -0.83
    ########.
    -0.73
     réguli
    -0.68
    dolu
    -0.67
    новништво
    -0.63
    OGND
    -0.63
     للمعارف
    -0.62
     JpaRepository
    -0.61
    POSITIVE LOGITS
     ultimately
    1.17
    Ultimately
    1.12
     Ultimately
    1.12
     uiteindelijk
    0.90
     letzt
    0.89
     finalement
    0.87
    indelijk
    0.77
     finally
    0.77
     eventually
    0.76
    結局
    0.75
    Activations Density 0.101%

    No Known Activations