© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15428
    Prev
    Next
    INDEX
    Explanations

    instances of the word "regular" and its variations, indicating a focus on regularity and consistency in activities or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onCreateView
    -0.61
     NSCoder
    -0.61
    StoryboardSegue
    -0.58
     Baillargeon
    -0.55
    pecabe
    -0.54
    MemoryWarning
    -0.54
    bootstrapcdn
    -0.54
    Autoritní
    -0.53
     defaultstate
    -0.52
    marvin
    -0.52
    POSITIVE LOGITS
     regular
    0.96
    regular
    0.94
     regularly
    0.92
     REGULAR
    0.92
     frequent
    0.91
    REGULAR
    0.87
    Regular
    0.87
     Regular
    0.84
     Frequent
    0.78
    frequent
    0.77
    Activations Density 0.174%

    No Known Activations