© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6902
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific programming and legal terms, particularly relating to functions and conditions in code or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Independencia
    -0.42
    aigu
    -0.38
     tasar
    -0.38
    '])){
    
    -0.38
    '));
    
    -0.37
     zru
    -0.37
    '))
    
    -0.36
     tunggal
    -0.36
     maternidade
    -0.36
     mē
    -0.35
    POSITIVE LOGITS
    تقاوى
    0.62
    ValueStyle
    0.56
     propOrder
    0.55
    الحياه
    0.54
    inWeight
    0.49
     minOccurs
    0.47
    AndEndTag
    0.46
     الحره
    0.45
     youre
    0.45
    IntoConstraints
    0.44
    Activations Density 1.219%

    No Known Activations