© 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. 25-GEMMASCOPE-RES-16K
    6. 8853
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people and places associated with the Scottish Parliament

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁥
    -1.00
    Cambodia
    -0.63
    Connecticut
    -0.60
     Cambodian
    -0.60
     Cambodia
    -0.60
    Karn
    -0.59
    Према
    -0.59
    meyer
    -0.58
    aarrggbb
    -0.57
     Karnataka
    -0.57
    POSITIVE LOGITS
     Scottish
    1.97
     Scotland
    1.87
    Scottish
    1.73
     Scots
    1.73
    Scotland
    1.67
     Glasgow
    1.59
     scottish
    1.56
     Edinburgh
    1.55
     Scot
    1.50
    scot
    1.50
    Activations Density 0.311%

    No Known Activations