© 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. 35-GEMMASCOPE-RES-16K
    6. 6910
    Prev
    Next
    INDEX
    Explanations

    mentions of celebrities and their social activities

    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
     mío
    -0.52
     adicionales
    -0.52
     ervaren
    -0.51
     administrativos
    -0.51
     économies
    -0.50
     regulares
    -0.50
     tapasztal
    -0.49
     antemano
    -0.48
     compleja
    -0.48
     cœurs
    -0.48
    POSITIVE LOGITS
     celebrities
    1.04
     Rihanna
    1.04
     Beyoncé
    1.02
     Kanye
    1.02
     Beyonce
    0.99
     celebs
    0.95
     Miley
    0.94
    Rihanna
    0.88
     Madonna
    0.88
     LeBron
    0.86
    Activations Density 0.472%

    No Known Activations