© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 17112
    Prev
    Next
    INDEX
    Explanations

    references to Sudan and its related geographical or political context

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

    Sudan and Western Sahara

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſch
    -0.60
     ſche
    -0.59
     ſte
    -0.58
     myſelf
    -0.56
     preſent
    -0.56
     autorytatywna
    -0.56
     faſt
    -0.54
     ſta
    -0.50
     Reſ
    -0.50
     cæ
    -0.48
    POSITIVE LOGITS
     Eritrea
    0.77
     Erit
    0.68
     Nub
    0.55
     Khartoum
    0.47
     Sudanese
    0.46
     Darfur
    0.45
    ashir
    0.43
    Sudan
    0.43
    Nub
    0.43
     Ethiopian
    0.42
    Activations Density 0.013%

    No Known Activations