© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3574
    Prev
    Next
    INDEX
    Explanations

    terms related to romantic relationships

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

    details about romantic relationships and partnerships.

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

    mentions of romantic relationships and statuses—partners, dating/engagement/marriage, breakups, and expressions of mutual affection and commitment.

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

    references to romantic relationships, particularly when describing couples, partners, boyfriends, girlfriends, or relationship timelines.

    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
    msgTypes
    -0.53
    totic
    -0.51
    ostar
    -0.51
    parsedMessage
    -0.50
    RectangleBorder
    -0.48
     erſt
    -0.47
     frigate
    -0.46
    mediator
    -0.46
     $_"
    -0.46
     queſta
    -0.46
    POSITIVE LOGITS
    enumi
    0.56
    ngdoc
    0.44
     ModelExpression
    0.41
    skjaer
    0.39
     kekasih
    0.38
     boyfriend
    0.38
     lovers
    0.35
    voerd
    0.35
    WebElementEntity
    0.34
    ClientSize
    0.34
    Activations Density 0.126%

    No Known Activations