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. 10-GEMMASCOPE-RES-16K
    6. 4982
    Prev
    Next
    INDEX
    Explanations

    references to diplomatic entities, positions, and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rosis
    -0.52
    zwald
    -0.51
     PKK
    -0.51
     Ezekiel
    -0.51
    ༘
    -0.50
     BoxFit
    -0.49
     Illinois
    -0.49
     Adirond
    -0.48
     Ventura
    -0.48
    вказ
    -0.48
    POSITIVE LOGITS
     diplomats
    0.96
     diplomatic
    0.95
     embassies
    0.93
     Diplomatic
    0.90
     embassy
    0.82
     diplomat
    0.80
    ambassade
    0.80
    Diplom
    0.80
     Embassy
    0.79
     diplom
    0.79
    Activations Density 0.102%

    No Known Activations