© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 35-GEMMASCOPE-RES-16K
    11. 5819
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to love and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Every
    -0.57
    Every
    -0.55
    every
    -0.50
     every
    -0.47
     todos
    -0.37
     모든
    -0.32
     todas
    -0.32
    gere
    -0.30
     tous
    -0.29
     tutte
    -0.29
    POSITIVE LOGITS
     eachother
    2.08
     varandra
    2.03
     друг
    1.98
     nhau
    1.97
     elkaar
    1.93
     einander
    1.66
    彼此
    1.63
     each
    1.58
     birbir
    1.54
    กัน
    1.45
    Activations Density 0.421%

    No Known Activations