© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 6594
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or streets in urban contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     siglos
    -0.70
     centuries
    -0.63
    expandindo
    -0.57
     secoli
    -0.56
    er
    -0.52
     aged
    -0.52
     auk
    -0.52
     nationalism
    -0.51
    SerializeField
    -0.50
    mes
    -0.50
    POSITIVE LOGITS
    "],
    
    0.85
    avenue
    0.84
     Avenue
    0.83
     proactive
    0.81
    )";
    
    0.78
    Avenue
    0.77
     innovative
    0.77
     AVENUE
    0.74
    innovative
    0.72
     Ave
    0.70
    Activations Density 0.085%

    No Known Activations