© 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. 1184
    Prev
    Next
    INDEX
    Explanations

    references to political ideologies and their outcomes

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

    Comparison or superlative adjectives

    np_acts-logits-general · gemini-2.0-flash

    clear victor or better

    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
     >=",
    -0.73
    RectangleBorder
    -0.67
    KURZBESCHREIBUNG
    -0.66
     another
    -0.65
    another
    -0.63
    "])
    -0.60
     Another
    -0.60
    Économie
    -0.57
    Another
    -0.57
     endforeach
    -0.56
    POSITIVE LOGITS
     dominant
    1.29
     predominate
    1.15
     dominance
    1.09
     dominates
    1.08
    dominant
    1.08
     dominate
    1.04
     Dominant
    1.04
     predominant
    1.03
     predominance
    1.02
     dominante
    1.02
    Activations Density 0.562%

    No Known Activations