© 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. 15824
    Prev
    Next
    INDEX
    Explanations

    terms related to governance, citizenship, and roles in societal structures

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

    possibly ending with "ship" or "hip"

    np_acts-logits-general · gemini-2.0-flash

    roles and affiliations

    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
    bootstrapcdn
    -0.77
     بيها
    -0.71
    Diwedd
    -0.69
    исленность
    -0.68
    zzleHttp
    -0.67
    
    -0.67
    Personendaten
    -0.66
    Ծանոթ
    -0.66
    TagMode
    -0.65
     DbType
    -0.63
    POSITIVE LOGITS
    SHIP
    0.81
    ship
    0.80
    hood
    0.71
     ship
    0.69
    Ship
    0.67
    ſhip
    0.67
    hip
    0.66
    انه
    0.64
    쉽
    0.62
    ism
    0.59
    Activations Density 0.372%

    No Known Activations