© 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. 21-GEMMASCOPE-RES-16K
    11. 1531
    Prev
    Next
    INDEX
    Explanations

    references to various programming concepts or code-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    -0.76
    es
    -0.70
    tory
    -0.70
    tale
    -0.64
    t
    -0.62
    a
    -0.58
    ture
    -0.57
    tation
    -0.55
    ه
    -0.54
    tative
    -0.53
    POSITIVE LOGITS
    nnnn
    0.84
     незавершена
    0.83
    nnn
    0.80
     kasarigan
    0.78
    RenderAtEndOf
    0.76
    ning
    0.76
     متعلقه
    0.75
    ned
    0.74
     nahilalakip
    0.73
    はじめに
    0.72
    Activations Density 0.453%

    No Known Activations