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. 2-GEMMASCOPE-RES-16K
    6. 15034
    Prev
    Next
    INDEX
    Explanations

    mentions of Donald Trump and significant controversies or emotions surrounding him

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.80
     وتسجيلات
    -0.79
     auffi
    -0.75
     BrowserModule
    -0.74
     ivelany
    -0.74
     Theſe
    -0.72
     snippetHide
    -0.72
     Prussia
    -0.71
     '
    
    -0.70
    hassee
    -0.70
    POSITIVE LOGITS
    大
    1.30
     大
    0.86
    的大
    0.73
     Villa
    0.72
    是大
    0.68
    大的
    0.62
    の大
    0.61
    小
    0.61
     lining
    0.60
    LAURA
    0.59
    Activations Density 0.087%

    No Known Activations