© 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. 15100
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and requests for information about family ancestry

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

    polite, conversational direct-address phrases in informal comments (greetings, gratitude/apologies, and contact or help requests between “I” and “you”).

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

    personal messages in informal online communication, particularly greetings, direct address, and expressions of gratitude or connection.

    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
    AndEndTag
    -0.75
     kasarigan
    -0.63
    ⟬
    -0.61
    ⤹
    -0.60
    setVerticalGroup
    -0.60
    Rhestr
    -0.60
    WebElementEntity
    -0.58
    saraba
    -0.58
     préfé
    -0.57
    httphttps
    -0.57
    POSITIVE LOGITS
    Cordialement
    0.39
     determin
    0.37
     Determin
    0.36
     grie
    0.36
    veget
    0.35
    url
    0.34
    PopupMenu
    0.34
    hello
    0.33
     update
    0.33
     судеб
    0.33
    Activations Density 0.091%

    No Known Activations