© 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. 7-GEMMASCOPE-RES-16K
    11. 15023
    Prev
    Next
    INDEX
    Explanations

    references to professional athletes and performers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reformas
    -0.45
     ThemeData
    -0.45
    Datuak
    -0.44
     rumahnya
    -0.43
     alturas
    -0.42
     destinos
    -0.41
    forRoot
    -0.41
     jantung
    -0.41
     šo
    -0.41
     faldas
    -0.41
    POSITIVE LOGITS
     athletes
    0.89
     athlete
    0.74
     Athletes
    0.72
     players
    0.66
     performers
    0.63
     footballers
    0.61
     Athlete
    0.61
    athletes
    0.60
    Athlete
    0.58
     footballer
    0.58
    Activations Density 0.418%

    No Known Activations