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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 252
    Prev
    Next
    INDEX
    Explanations

    references to various "sites" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.75
     bezeichneter
    -0.72
    Hauptartikel
    -0.68
    ‘’
    -0.64
    )”
    -0.64
    ”、“
    -0.63
    Quelles
    -0.62
    تفصیلات
    -0.61
     voul
    -0.61
     Kearney
    -0.60
    POSITIVE LOGITS
     Site
    2.71
     Sites
    2.68
     site
    2.67
     sites
    2.60
    Site
    2.53
    SITE
    2.52
     SITE
    2.51
    Sites
    2.38
    sites
    2.38
    site
    2.37
    Activations Density 0.049%

    No Known Activations