© 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. 21-GEMMASCOPE-RES-16K
    11. 13643
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and related expressions in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.64
     AssemblyTitle
    -0.63
     nakalista
    -0.62
    
    -0.60
    JoinTable
    -0.58
    HtmlAttribute
    -0.55
    gypti
    -0.52
    writeFieldEnd
    -0.52
     intptr
    -0.51
     विश्वसनीयता
    -0.50
    POSITIVE LOGITS
    Personendaten
    0.37
     gyhoeddwyd
    0.32
     aikaa
    0.30
    ніципалі
    0.30
    Choice
    0.30
     kemarin
    0.29
    Ծանոթ
    0.28
     चीज़ों
    0.28
     aikana
    0.28
     Choice
    0.27
    Activations Density 1.836%

    No Known Activations