© 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. 15316
    Prev
    Next
    INDEX
    Explanations

    references to political statements and decisions

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

    Titles of political figures

    np_acts-logits-general · gemini-2.0-flash

    political leaders and titles

    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
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.66
     resourceCulture
    -0.59
     Spacer
    -0.55
    ViewFeatures
    -0.52
    isseurs
    -0.51
     promocional
    -0.51
    انجليز
    -0.50
     nativo
    -0.49
     espel
    -0.48
     vorbehalten
    -0.48
    POSITIVE LOGITS
     Minister
    1.34
     ministers
    1.31
     minister
    1.29
     Cabinet
    1.28
     government
    1.27
     Prime
    1.26
     Ministers
    1.24
     Government
    1.21
     cabinet
    1.20
     Parliament
    1.16
    Activations Density 0.609%

    No Known Activations