© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 7282
    Prev
    Next
    INDEX
    Explanations

    references to mathematical sets and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    canes
    -0.58
     ویکی‌پدیای
    -0.55
     sebenar
    -0.53
    ToBe
    -0.51
     mere
    -0.50
     zugleich
    -0.49
    iritual
    -0.49
     utama
    -0.49
    grès
    -0.49
     главное
    -0.49
    POSITIVE LOGITS
    subset
    1.57
     subset
    1.26
     subsets
    1.04
    subseteq
    0.90
     handful
    0.88
    ⊂
    0.83
    Subset
    0.81
    NameInMap
    0.79
     dozen
    0.79
    а
    0.76
    Activations Density 0.085%

    No Known Activations