© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 8980
    Prev
    Next
    INDEX
    Explanations

    repeated periods and ellipses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -0.87
    awtextra
    -0.85
    Gambas
    -0.84
     tartalomajánló
    -0.83
    RectangleBorder
    -0.81
    ToScroll
    -0.78
    ribune
    -0.77
    LayoutStyle
    -0.77
    "?>
    -0.76
    出版年
    -0.76
    POSITIVE LOGITS
     and
    0.69
     of
    0.61
    ๆ
    0.58
    ்கள்
    0.54
     rendus
    0.50
     or
    0.48
    [toxicity=0]
    0.48
     geweest
    0.48
     be
    0.47
     that
    0.47
    Activations Density 0.503%

    No Known Activations