© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106099
    Prev
    Next
    INDEX
    Explanations

    specific numeric values, especially related to measurements and comparisons, within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ToAction
    -0.39
    精
    -0.39
     studying
    -0.34
    queles
    -0.31
     einz
    -0.29
    siapkan
    -0.29
    mainAxisSize
    -0.29
     付
    -0.28
     sharply
    -0.28
     oneself
    -0.28
    POSITIVE LOGITS
    ніципалі
    0.71
     defaultstate
    0.66
     NSCoder
    0.62
    出版年
    0.57
    InputTagHelper
    0.57
    StoryboardSegue
    0.56
    IsMutable
    0.56
     Numerade
    0.55
    tanleria
    0.55
     мәкал
    0.54
    Activations Density 0.070%

    No Known Activations