© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6096
    Prev
    Next
    INDEX
    Explanations

    references to political and financial corruption

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

    political events and political figures' names.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    news-style expository passages that present factual descriptions of entities, actions, and details like dates, numbers, and official announcements

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    references to specific historical events, particularly political scandals or significant moments involving named individuals.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     varier
    -0.35
     coucher
    -0.35
    guiente
    -0.33
     quizá
    -0.32
     nakalista
    -0.32
    spesies
    -0.29
    AutoField
    -0.29
    GOTREF
    -0.29
    nonatomic
    -0.28
    ędzie
    -0.28
    POSITIVE LOGITS
     OFDb
    0.77
     surla
    0.73
     وتسجيلات
    0.66
    новништво
    0.61
    AISSEE
    0.60
    TypedDataSet
    0.57
     Italijanski
    0.56
     InputDecoration
    0.56
    ReusableCell
    0.55
    NamedQueries
    0.54
    Activations Density 0.514%

    No Known Activations