© 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. 9-GEMMASCOPE-RES-131K
    11. 55480
    Prev
    Next
    INDEX
    Explanations

    references to military or fire-related units

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

    Brigade and Brigham Young

    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
    clusal
    -0.46
     Holanda
    -0.46
    alleye
    -0.43
    gebob
    -0.42
    MemoryWarning
    -0.41
     Californie
    -0.40
     Wartawan
    -0.39
    LookAnd
    -0.38
     NSCoder
    -0.37
    Jawaban
    -0.36
    POSITIVE LOGITS
     Brigade
    2.23
     brigade
    2.13
     brigades
    1.80
     Brig
    1.79
     BRIG
    1.77
    Brig
    1.62
    brig
    1.48
     brig
    1.46
     брига
    1.30
     Brigadier
    1.20
    Activations Density 0.004%

    No Known Activations