© 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. 20-GEMMASCOPE-RES-131K
    6. 75713
    Prev
    Next
    INDEX
    Explanations

    references to the United Arab Emirates and its various programs or initiatives

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

    United Arab Emirates and cities

    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
    (;;)
    -0.53
    __":
    -0.48
     المعيارى
    -0.47
    ]='\
    -0.46
    tagHelperRunner
    -0.46
     ErrIntOverflow
    -0.45
    ')")
    -0.45
    UIControlState
    -0.45
     onAnimation
    -0.45
    ).}
    -0.45
    POSITIVE LOGITS
     Dhabi
    1.28
     Dubai
    1.19
     UAE
    1.10
    Dubai
    1.05
    UAE
    0.91
     dubai
    0.91
     Emirates
    0.89
     Zayed
    0.86
     Emir
    0.85
     emirates
    0.84
    Activations Density 0.006%

    No Known Activations