© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8908
    Prev
    Next
    INDEX
    Explanations

    terms related to political entities and conflicts, particularly involving Cambodia and associated groups

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

    Cambodia or Cambodian people

    np_acts-logits-general · gemini-2.0-flash

    Chi Thon Ngo and Cambodian names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     milano
    -0.60
     ErrIntOverflow
    -0.60
     Lagos
    -0.60
     Donegal
    -0.60
    celotti
    -0.59
    ័
    -0.59
    ៊
    -0.59
    MigrationBuilder
    -0.58
     Nigerian
    -0.57
     Nigeria
    -0.57
    POSITIVE LOGITS
     Cambodia
    1.34
     Cambodian
    1.33
     Phnom
    1.23
    Cambodia
    1.20
     Khmer
    1.19
    Cambo
    1.06
     Cambo
    0.99
    柬
    0.85
     Penh
    0.79
     Sie
    0.78
    Activations Density 0.031%

    No Known Activations