© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 12502
    Prev
    Next
    INDEX
    Explanations

    references to Brazil and its cultural or political elements

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

    Brazil and Brazilian

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Nugent
    -0.39
     op
    -0.39
     opp
    -0.38
     Vann
    -0.38
     Otero
    -0.38
    Lydia
    -0.37
    <sub>
    -0.37
    <strong>
    -0.36
     Op
    -0.36
    <em>
    -0.36
    POSITIVE LOGITS
     Brazil
    1.86
    Brazil
    1.80
     Brazilian
    1.65
     Braz
    1.56
     BRAZIL
    1.55
    Brazilian
    1.55
     brazil
    1.52
     Brésil
    1.48
    Braz
    1.45
     Brasil
    1.38
    Activations Density 0.007%

    No Known Activations