© 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-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5614
    Prev
    Next
    INDEX
    Explanations

    various forms and contexts of the word "pattern"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DotNetBar
    -0.90
    PerformLayout
    -0.84
    CURLOPT
    -0.79
    ixeira
    -0.70
     riscal
    -0.69
     <>",
    -0.68
     enctype
    -0.68
     íntimo
    -0.67
    DllImport
    -0.67
    opsida
    -0.67
    POSITIVE LOGITS
     pattern
    3.73
     patterns
    3.48
     Pattern
    3.48
    pattern
    3.33
     Patterns
    3.29
     PATTERN
    3.27
    Pattern
    3.23
    Patterns
    2.98
    patterns
    2.85
    PATTERN
    2.56
    Activations Density 0.064%

    No Known Activations