© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12694
    Prev
    Next
    INDEX
    Explanations

    references to historical political events and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns referring to countries, nationalities, and political leaders.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     italienischen
    -0.56
    Illinois
    -0.52
     transfieras
    -0.52
     griechischen
    -0.52
     препратки
    -0.51
     brasileño
    -0.50
     Illinois
    -0.50
     Kalifor
    -0.50
     niyang
    -0.50
     mukaan
    -0.50
    POSITIVE LOGITS
     country
    1.05
     nation
    0.96
     countrymen
    0.88
     government
    0.86
     país
    0.79
     national
    0.78
    country
    0.73
     nationals
    0.73
     citizens
    0.70
    国民
    0.70
    Activations Density 0.613%

    No Known Activations