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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6765
    Prev
    Next
    INDEX
    Explanations

    references to racial issues and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    bitField
    -0.53
    eltjes
    -0.51
    makeConstraints
    -0.48
     henvis
    -0.46
    LayoutConstraint
    -0.44
    انجليز
    -0.42
    تفصیلات
    -0.42
    Begriffsklä
    -0.41
     सत्यापित
    -0.41
     Wikimedijinoj
    -0.41
    POSITIVE LOGITS
     intermediate
    2.09
     middle
    1.87
    intermediate
    1.85
    middle
    1.77
     intermedio
    1.71
     Intermediate
    1.70
    中間
    1.65
     midway
    1.64
     intermediary
    1.63
     intermédiaire
    1.63
    Activations Density 0.526%

    No Known Activations