© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1966
    Prev
    Next
    INDEX
    Explanations

    narratives involving love and emotional connections in complex situations

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

    love and romance

    np_acts-logits-general · gemini-2.0-flash

    love

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RefNanny
    -0.50
    EndContext
    -0.44
     Pert
    -0.43
    postcss
    -0.41
    議院
    -0.40
     peggio
    -0.40
    gridy
    -0.40
    versaire
    -0.39
     impedance
    -0.39
    bufio
    -0.39
    POSITIVE LOGITS
     love
    1.90
     romantic
    1.59
     romance
    1.56
    love
    1.54
     Love
    1.51
     LOVE
    1.48
    Love
    1.43
     loves
    1.41
    LOVE
    1.37
     amour
    1.36
    Activations Density 0.224%

    No Known Activations