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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9907
    Prev
    Next
    INDEX
    Explanations

    references to British entities or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parlato
    -0.55
     andata
    -0.55
     Petru
    -0.52
    jsoup
    -0.51
     solidity
    -0.50
     sillas
    -0.50
     înc
    -0.50
     comptes
    -0.50
    Demografia
    -0.49
    målet
    -0.48
    POSITIVE LOGITS
    British
    0.95
    Britain
    0.90
     British
    0.88
     Britain
    0.83
     glyphicon
    0.82
     BRITISH
    0.81
     kasarigan
    0.81
     Brits
    0.81
     british
    0.79
     DBNull
    0.75
    Activations Density 0.038%

    No Known Activations