Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6457
    Prev
    Next
    INDEX
    Explanations

    references to political statements and actions

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

    Preceding specific punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    diplomatic and foreign policy terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schot
    -0.51
     Afrikaans
    -0.48
    ViewFeatures
    -0.46
     wales
    -0.46
    toje
    -0.46
    Nirvana
    -0.46
     konsumen
    -0.45
    regation
    -0.45
     loisirs
    -0.45
    lük
    -0.43
    POSITIVE LOGITS
     diplomatic
    1.17
     bilateral
    1.07
     diplomacy
    1.06
     diplomats
    0.94
     Foreign
    0.94
     multilateral
    0.94
     diplom
    0.93
    diplom
    0.93
     Diplomatic
    0.89
     Bilateral
    0.84
    Activations Density 0.542%

    No Known Activations