© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6684
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical relations and events, particularly focusing on the Middle East region and its countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.47
    o
    -0.45
     $\
    -0.42
    p
    -0.42
     "
    -0.41
     MacArthur
    -0.41
    psz
    -0.41
    ↵↵
    -0.40
    g
    -0.39
    /
    -0.39
    POSITIVE LOGITS
     Dubai
    1.34
     UAE
    1.32
    Dubai
    1.31
     Dhabi
    1.29
     dubai
    1.23
    UAE
    1.18
    GEBURTSDATUM
    1.16
    Geplaatst
    1.16
    contentLoaded
    1.12
     emirates
    1.11
    Activations Density 0.120%

    No Known Activations