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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 6468
    Prev
    Next
    INDEX
    Explanations

    references to political parties, specifically the Democrats and Republicans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aux
    -0.51
     nas
    -0.51
    web
    -0.50
     por
    -0.50
    msup
    -0.48
    aux
    -0.47
    peri
    -0.47
    â
    -0.47
     visi
    -0.46
    a
    -0.46
    POSITIVE LOGITS
    SpringRunner
    1.02
    InjectMocks
    0.96
    AccessorTable
    0.95
    parsedMessage
    0.95
     propOrder
    0.94
    AlterField
    0.92
     mourut
    0.88
    setupUi
    0.88
    migrationBuilder
    0.87
     betweenstory
    0.87
    Activations Density 0.169%

    No Known Activations