© 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. 4895
    Prev
    Next
    INDEX
    Explanations

    content related to parenting and baby supplies, specifically focusing on sizes and recommendations for newborn items

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

    technical details about measurement, sizing, and specifications, particularly related to products like diapers, servers, or computer configurations.

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

    second-person advice and recommendations, including instructional suggestions and troubleshooting guidance.

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

    advisory or suggestive language, particularly words like "should," "try," "could," "recommend," and phrases giving advice or possibilities.

    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
    
    -0.50
    RenderAtEndOf
    -0.49
    SharedCtor
    -0.47
     onStop
    -0.47
    makeText
    -0.42
    tagHelper
    -0.41
    yntaxException
    -0.41
    alignItems
    -0.41
    AsUp
    -0.41
     consultato
    -0.40
    POSITIVE LOGITS
     IIRC
    0.59
     IMHO
    0.56
     yourself
    0.56
     iirc
    0.52
     maybe
    0.50
     informée
    0.50
    wapV
    0.49
     IMO
    0.48
     prolly
    0.48
     you
    0.46
    Activations Density 0.525%

    No Known Activations