© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8902
    Prev
    Next
    INDEX
    Explanations

    references to "patterns" and "pattern recognition"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CURLOPT
    -0.94
    PerformLayout
    -0.93
     íntimo
    -0.88
     مرئيه
    -0.87
    balanceOf
    -0.86
    outchouc
    -0.85
    קישורים
    -0.84
     doPost
    -0.83
     CURLOPT
    -0.81
    ilibrium
    -0.80
    POSITIVE LOGITS
     patterns
    2.05
     pattern
    2.01
     Patterns
    1.84
     Pattern
    1.79
     PATTERN
    1.74
    Patterns
    1.73
    Pattern
    1.69
    pattern
    1.68
    patterns
    1.56
    TERNS
    1.45
    Activations Density 0.061%

    No Known Activations