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. 3-GEMMASCOPE-RES-16K
    6. 5831
    Prev
    Next
    INDEX
    Explanations

    references to U.S. interventionism and its implications in foreign politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.81
    AutoScaleMode
    -0.77
     AssemblyProduct
    -0.76
    tangentMode
    -0.75
    LookAnd
    -0.75
     ویکی‌پدیای
    -0.74
     تضيفلها
    -0.73
    sonaro
    -0.70
    phosa
    -0.69
     @}
    -0.68
    POSITIVE LOGITS
     business
    0.44
     Grade
    0.44
    ↵
    0.41
    thrift
    0.41
     fritas
    0.40
     employees
    0.39
    moveToFirst
    0.38
    اعمال
    0.38
     talento
    0.38
    สือ
    0.38
    Activations Density 0.919%

    No Known Activations