© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 127034
    Prev
    Next
    INDEX
    Explanations

    concepts related to statistical validity and definitions of terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    حياته
    -0.40
    
    -0.39
    esModule
    -0.37
     stället
    -0.37
    fortawesome
    -0.37
     utilidad
    -0.36
    AnimationsModule
    -0.35
    حياتها
    -0.35
    󠁮
    -0.34
    請繼續往下閱讀
    -0.33
    POSITIVE LOGITS
     Administrativna
    0.59
     lenker
    0.57
     Biôgrafia
    0.52
    وصلات
    0.51
     nonUne
    0.50
    meaning
    0.50
     Bioaccumulative
    0.50
     meaning
    0.49
    CodeAnalysis
    0.48
    sekolah
    0.46
    Activations Density 0.110%

    No Known Activations