© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 119788
    Prev
    Next
    INDEX
    Explanations

    references to Nigeria and Nigerian individuals or entities

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

    Nigeria and Nigerian

    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
     пом
    -0.41
    spec
    -0.39
     Hecht
    -0.38
     Whitfield
    -0.37
    Respect
    -0.36
    U
    -0.36
    Sp
    -0.36
     cost
    -0.36
    +
    -0.34
     tip
    -0.34
    POSITIVE LOGITS
     Nigerian
    1.99
     Nigeria
    1.96
    Nigeria
    1.77
    Nigerian
    1.77
     Nigerians
    1.60
     NIGERIA
    1.52
     niger
    1.50
     NIGER
    1.32
    niger
    1.28
    Niger
    1.12
    Activations Density 0.004%

    No Known Activations