© 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. 20-GEMMASCOPE-RES-16K
    11. 807
    Prev
    Next
    INDEX
    Explanations

    references to influential individuals and their actions or statements

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

    Conspiracy theories/Deep state content

    np_acts-logits-general · gemini-2.0-flash

    conspiracy terms and contractions

    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
    •LR features
    Conspiracy Features

    No Comments

    Negative Logits
    MigrationBuilder
    -0.74
    IVEREF
    -0.72
    ContentAsync
    -0.66
     Мексичка
    -0.66
     AssemblyCulture
    -0.66
    addCriterion
    -0.65
    PreferredItem
    -0.64
     iprot
    -0.62
     mecánico
    -0.60
     utafitiHapana
    -0.59
    POSITIVE LOGITS
     (((
    0.70
     cabal
    0.66
     Rothschild
    0.65
     libert
    0.62
     Soros
    0.61
     Biden
    0.59
     https
    0.58
     Trump
    0.57
     Bilder
    0.57
     freedom
    0.56
    Activations Density 0.785%

    No Known Activations