Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10678
    Prev
    Next
    INDEX
    Explanations

    events related to romantic relationships and engagements

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

    proposals or engagements

    np_acts-logits-general · gemini-2.0-flash

    propose and engagement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     אס
    -0.36
    épaisseur
    -0.35
    文档
    -0.35
     lác
    -0.35
    usters
    -0.35
    InvalidArgument
    -0.33
     plate
    -0.33
    Py
    -0.32
     Rie
    -0.32
    UseVisualStyle
    -0.32
    POSITIVE LOGITS
     engagement
    1.48
     Engagement
    1.36
    Engagement
    1.30
    engagement
    1.24
     engaged
    1.17
     engagements
    1.16
     Engaged
    1.15
     Engage
    1.14
     proposal
    1.13
     propose
    1.11
    Activations Density 0.114%

    No Known Activations