© 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. 18-GEMMASCOPE-RES-16K
    11. 11573
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations

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

    Expressions with math symbols

    np_acts-logits-general · gemini-2.0-flash

    math and code symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -1.30
    ,
    -1.21
    .
    -1.12
     (
    -0.99
     and
    -0.97
     a
    -0.95
    :
    -0.94
     in
    -0.93
    ;
    -0.92
      
    -0.91
    POSITIVE LOGITS
     myſelf
    1.68
     itſelf
    1.58
     pleaſure
    1.54
     purpoſe
    1.52
    تقاوى
    1.51
     Anſ
    1.49
     дописавши
    1.49
     ་་
    1.47
     reaſon
    1.46
     greateſt
    1.46
    Activations Density 1.168%

    No Known Activations