© 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. 28-GEMMASCOPE-RES-16K
    11. 9059
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and love in relationships

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

    before or after "love"

    np_acts-logits-general · gemini-2.0-flash

    love you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prnewswire
    -0.57
    scriptcase
    -0.50
    tamol
    -0.47
     ſind
    -0.47
    INCREF
    -0.46
     Kenyans
    -0.45
     frustrated
    -0.45
     polite
    -0.44
     politely
    -0.44
     masque
    -0.44
    POSITIVE LOGITS
     love
    0.90
     loving
    0.82
    love
    0.80
     Love
    0.76
     LOVE
    0.73
    Love
    0.71
     loves
    0.68
    Loving
    0.68
    LOVE
    0.68
    loves
    0.66
    Activations Density 0.159%

    No Known Activations