© 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. 270
    Prev
    Next
    INDEX
    Explanations

    references to political positions and roles within government structures

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

    Titles of leaders or officials

    np_acts-logits-general · gemini-2.0-flash

    appointed leader

    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
     مُعرِّف
    -0.76
     Мексичка
    -0.56
     Vikipedi
    -0.55
    ัติ
    -0.47
     /\.(
    -0.46
    enschappelijke
    -0.46
    الحياه
    -0.45
    ("."
    -0.45
    Autoritní
    -0.45
     ffilmiau
    -0.44
    POSITIVE LOGITS
     president
    1.65
     President
    1.54
     chairman
    1.46
     Chairman
    1.39
     CEO
    1.37
    President
    1.35
    president
    1.35
     chief
    1.33
     Chief
    1.30
     head
    1.23
    Activations Density 0.523%

    No Known Activations