© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8813
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sneaked."

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

    German language related words

    np_acts-logits-general · gemini-2.0-flash

    German and English phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.65
     textStatus
    -0.61
     snippetHide
    -0.61
     للاسماء
    -0.59
     ویکی‌پدیای
    -0.58
    存于互联网档案馆
    -0.57
    
    -0.56
    typeparam
    -0.55
    stdc
    -0.55
    upassen
    -0.53
    POSITIVE LOGITS
     solitaire
    0.56
    Schemes
    0.56
     Regist
    0.56
    jsdelivr
    0.56
     daß
    0.53
     Airways
    0.52
     Wegen
    0.52
     lecz
    0.51
     Raff
    0.50
    __).
    0.49
    Activations Density 0.116%

    No Known Activations