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. 20-GEMMASCOPE-RES-16K
    6. 14557
    Prev
    Next
    INDEX
    Explanations

    references to "context" in various forms and usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "context" and its variations

    np_acts-logits-general · gemini-2.0-flash

    context / ctx

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ագրություններ
    -0.85
     Commencez
    -0.73
    ✨:
    -0.70
    RenderAtEndOf
    -0.68
    multer
    -0.67
    MessageTagHelper
    -0.67
    
    -0.67
    İstinadlar
    -0.65
    idopsis
    -0.64
    Erreferentziak
    -0.64
    POSITIVE LOGITS
    ually
    0.88
     ctx
    0.84
    ual
    0.80
     useContext
    0.79
     contexts
    0.77
     context
    0.76
     CONTEXT
    0.76
     getContext
    0.75
     AspNetCore
    0.75
     Context
    0.70
    Activations Density 0.102%

    No Known Activations