© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10850
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or organizations and their activities over time

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

    time periods spanning multiple years or decades.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     okuyayım
    -0.60
     onCreateView
    -0.59
    ViewFeatures
    -0.56
    LLocation
    -0.55
    存于互联网档案馆
    -0.55
     AssemblyTitle
    -0.55
    лтемелер
    -0.54
    tanleria
    -0.54
     bezeichneter
    -0.53
    tangentMode
    -0.52
    POSITIVE LOGITS
     has
    1.80
     telah
    1.67
     đã
    1.41
     have
    1.22
     hasn
    1.05
     olmuş
    0.99
     haberse
    0.98
     hemos
    0.96
     heeft
    0.93
     نے
    0.93
    Activations Density 2.300%

    No Known Activations