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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 101628
    Prev
    Next
    INDEX
    Explanations

    instances of the word "treat" and its variations, indicating a focus on the treatment of individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     IndexPath
    -0.48
    CodeAnalysis
    -0.46
    shadowOffset
    -0.45
     Pallas
    -0.43
    Bioaccumulative
    -0.42
     Indigo
    -0.42
    Fabian
    -0.41
    ungkinkan
    -0.41
     schoolmaster
    -0.41
     Picchu
    -0.41
    POSITIVE LOGITS
    treat
    0.94
     Treat
    0.94
     treat
    0.93
     treated
    0.93
     Treating
    0.90
    Treating
    0.88
    Treat
    0.87
     treating
    0.86
     Treated
    0.86
     TREAT
    0.84
    Activations Density 0.030%

    No Known Activations