© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 5829
    Prev
    Next
    INDEX
    Explanations

    legal terms and references to judicial proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    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
     Insee
    -0.58
     الاطلاع
    -0.58
    render
    -0.58
     مشين
    -0.57
    publique
    -0.57
     render
    -0.54
     rendering
    -0.54
     Nore
    -0.54
     doors
    -0.54
    POSITIVE LOGITS
     supporters
    0.54
    Посилання
    0.53
    脚注の使い方
    0.52
     lancar
    0.49
    iented
    0.48
    Демографія
    0.48
     versus
    0.47
    AsUp
    0.47
     vantagem
    0.46
     المتحدة
    0.46
    Activations Density 0.604%

    No Known Activations