© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 128828
    Prev
    Next
    INDEX
    Explanations

    words related to reinforcement and reinforcement processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    reinforce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Negative Logits
     informée
    -0.57
     تعدى
    -0.56
     nakalista
    -0.54
    astéroïdes
    -0.50
     kasarigan
    -0.49
    AsUp
    -0.47
    Timmy
    -0.45
     abz
    -0.45
    jsonwebtoken
    -0.44
    Domen
    -0.44
    POSITIVE LOGITS
     reinforced
    1.88
     reinforcement
    1.86
     reinforce
    1.80
     Reinforced
    1.70
     Reinforcement
    1.65
    reinforced
    1.64
     reinforcing
    1.62
     reinforces
    1.55
     reinforcements
    1.45
    Rein
    1.41
    Activations Density 0.004%

    No Known Activations