© 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 - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12858
    Prev
    Next
    INDEX
    Explanations

    references to Scottish entities, particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cérebro
    -0.60
     résumé
    -0.60
    classpath
    -0.59
    괄
    -0.58
    Azur
    -0.56
     Sien
    -0.56
    эффици
    -0.56
     Delano
    -0.55
    bno
    -0.54
     chinoise
    -0.54
    POSITIVE LOGITS
     Scottish
    1.70
     Scotland
    1.70
    Scotland
    1.62
     Scots
    1.59
     scottish
    1.58
    Scottish
    1.51
     Scotsman
    1.30
     Glasgow
    1.28
     Scotch
    1.27
     scot
    1.26
    Activations Density 0.619%

    No Known Activations