© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 8720
    Prev
    Next
    INDEX
    Explanations

    references to tribes and tribal leadership

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

    tribal groups, chiefs, and warfare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PSS
    -0.50
    money
    -0.44
    Ỏ
    -0.43
    Aurora
    -0.43
     Secured
    -0.43
    URLException
    -0.43
     Hadid
    -0.43
    かしい
    -0.42
    OMO
    -0.42
    secured
    -0.42
    POSITIVE LOGITS
     tribe
    1.16
     Tribe
    1.16
     tribes
    1.12
    Tribe
    1.10
    tribe
    0.97
     Tribes
    0.96
    Tribal
    0.93
     tribal
    0.90
     Tribal
    0.90
    tribal
    0.76
    Activations Density 0.004%

    No Known Activations