© 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. 104011
    Prev
    Next
    INDEX
    Explanations

    terms related to specific types of microorganisms and their characteristics

    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
     thin
    -0.36
     тон
    -0.29
     en
    -0.28
     string
    -0.27
    string
    -0.25
     dün
    -0.25
     хви
    -0.25
     graduated
    -0.25
    7
    -0.25
     A
    -0.24
    POSITIVE LOGITS
     resourceCulture
    1.05
    EndGlobalSection
    0.93
    setVerticalGroup
    0.88
    expandindo
    0.86
    
    0.78
     autorytatywna
    0.78
     समीक्षाओं
    0.77
    Hentet
    0.77
    Geplaatst
    0.75
    EndInit
    0.74
    Activations Density 0.217%

    No Known Activations