© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57726
    Prev
    Next
    INDEX
    Explanations

    references to Barcelona and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Astor
    -0.79
    
    -0.66
    getDoctrine
    -0.65
    databind
    -0.64
     Jind
    -0.64
     IRS
    -0.64
    Morrison
    -0.63
     ongles
    -0.61
    SourceChecksum
    -0.60
     Tiberius
    -0.59
    POSITIVE LOGITS
    CELONA
    1.73
     Barcelona
    1.66
    Barcelona
    1.55
     Barca
    1.36
     Catalan
    1.29
     Catalunya
    1.23
     Cataluña
    1.20
     Barcelone
    1.18
    Catal
    1.17
     Barça
    1.17
    Activations Density 0.029%

    No Known Activations