© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8408
    Prev
    Next
    INDEX
    Explanations

    references to political events and controversies

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

    Follows "President", "Trump", or "DDT"

    np_acts-logits-general · gemini-2.0-flash

    Donald Trump, Russia, obstruction, presidential eligibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Copia
    -0.61
    queryInterface
    -0.58
     lokale
    -0.57
     locals
    -0.56
     onBind
    -0.56
     Locals
    -0.55
    EndInit
    -0.55
     locally
    -0.55
     locaux
    -0.55
    ijnt
    -0.54
    POSITIVE LOGITS
     presidential
    1.42
     Presidential
    1.29
     President
    1.28
     Trump
    1.26
    Presidential
    1.17
    President
    1.16
    Trump
    1.16
     presidencial
    1.11
     Biden
    1.04
     president
    1.03
    Activations Density 0.782%

    No Known Activations