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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3493
    Prev
    Next
    INDEX
    Explanations

    terms related to seniority or positions in hierarchy

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

    Preceding titles like "Director", "Justice," or "Vice"

    np_acts-logits-general · gemini-2.0-flash

    senior followed by a title

    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
    //
    -0.72
    évaluateur
    -0.65
    %)$
    -0.61
    PMailer
    -0.57
    ParallelGroup
    -0.56
    axa
    -0.54
     pinulongan
    -0.54
    Havolalar
    -0.54
     quizás
    -0.53
    InstanceState
    -0.52
    POSITIVE LOGITS
     citizen
    0.96
     citizens
    0.84
     Citizen
    0.83
     Citizens
    0.79
    Citizen
    0.78
    ity
    0.78
     statesman
    0.75
    Citizens
    0.73
    citizen
    0.73
     statesmen
    0.68
    Activations Density 0.056%

    No Known Activations