© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14151
    Prev
    Next
    INDEX
    Explanations

    specific names of countries and regions

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

    lists of geographical locations, particularly countries and regions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    geographic locations, particularly countries and regions, often in lists or enumerations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of countries or regions, especially geopolitical entities appearing in lists or jurisdictional contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
    MessageTagHelper
    -0.45
     onStop
    -0.40
    Aholisi
    -0.40
    Rusia
    -0.39
    Allemagne
    -0.38
    amsmath
    -0.38
     paulista
    -0.38
     Итали
    -0.38
    LabelTagHelper
    -0.37
    Bologna
    -0.37
    POSITIVE LOGITS
     territories
    0.90
     islands
    0.79
     Cayman
    0.78
     Territories
    0.77
     Guam
    0.77
     Falkland
    0.73
    territ
    0.73
     Gibraltar
    0.71
     Bermuda
    0.71
     Islands
    0.70
    Activations Density 0.443%

    No Known Activations