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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 4127
    Prev
    Next
    INDEX
    Explanations

    references to freedom and liberty in political contexts

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

    America, Americans, or American ideals

    np_acts-logits-general · gemini-2.0-flash

    American liberty and government

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     متعلقه
    -0.88
     تضيفلها
    -0.79
    出版年
    -0.74
    bigliamento
    -0.74
     >=",
    -0.72
     disponibilités
    -0.72
    OGND
    -0.68
    parsedMessage
    -0.65
    évaluateur
    -0.65
     Савезне
    -0.62
    POSITIVE LOGITS
     America
    1.00
     nation
    0.91
    America
    0.87
     Americans
    0.85
     patriotic
    0.85
     American
    0.84
     liberty
    0.83
     patriotism
    0.80
     freedoms
    0.76
     america
    0.76
    Activations Density 0.347%

    No Known Activations