© 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. 1797
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations and their political contexts

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

    geographical locations and place names, particularly Middle Eastern and North African cities and countries.

    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
     DKK
    -0.39
     CreateTagHelper
    -0.39
     Vedas
    -0.38
    Kariera
    -0.35
     bav
    -0.34
    ungkan
    -0.34
    mathsf
    -0.34
    JvmStatic
    -0.33
     Indra
    -0.33
     tren
    -0.33
    POSITIVE LOGITS
     Lebanese
    1.38
     Beirut
    1.30
     Lebanon
    1.25
    Lebanon
    1.11
     Arab
    1.02
     Syrian
    0.98
     Syria
    0.97
     Hezbollah
    0.94
    Arab
    0.90
     Arabic
    0.88
    Activations Density 0.191%

    No Known Activations