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. 14848
    Prev
    Next
    INDEX
    Explanations

    references to capital and financial terms related to expenditures

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

    "capital" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    capital offenses, punishment, city, expenditure

    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
    ̍
    -0.77
     aveug
    -0.75
     Toussaint
    -0.74
    noaa
    -0.73
     Winaray
    -0.73
    |}{}
    -0.67
     Feynman
    -0.67
    Vidite
    -0.67
     referrerpolicy
    -0.66
     Flücht
    -0.66
    POSITIVE LOGITS
    CAPITAL
    0.97
     capital
    0.96
     Capital
    0.92
     CAPITAL
    0.91
    capital
    0.87
    Capital
    0.86
     capitales
    0.77
     متعلقه
    0.75
     kapital
    0.75
     capitalized
    0.71
    Activations Density 0.055%

    No Known Activations