© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 66195
    Prev
    Next
    INDEX
    Explanations

    phrases indicating regret or missed opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    should have been earlier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actuellement
    -0.40
     même
    -0.38
     slightly
    -0.38
     derzeit
    -0.37
     currently
    -0.35
     mesmo
    -0.35
    currently
    -0.34
    slightly
    -0.34
     very
    -0.33
     future
    -0.33
    POSITIVE LOGITS
     sooner
    1.27
     earlier
    1.15
    earlier
    1.08
     Earlier
    0.95
    Earlier
    0.90
     wcześniej
    0.85
     vorher
    0.78
     eerder
    0.75
    早在
    0.74
    早就
    0.73
    Activations Density 0.045%

    No Known Activations