© 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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11529
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "United States" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.82
    Personensuche
    -0.79
    parsedMessage
    -0.79
    rungsseite
    -0.79
    verwijspagina
    -0.72
    elemField
    -0.69
    principalColumn
    -0.68
     مشين
    -0.68
     الرياضيه
    -0.68
    RegressionTest
    -0.67
    POSITIVE LOGITS
     United
    0.86
     New
    0.75
     San
    0.67
     North
    0.65
    United
    0.60
     South
    0.59
     UNITED
    0.58
     Los
    0.56
     West
    0.56
     Middle
    0.56
    Activations Density 0.169%

    No Known Activations