© 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. 0-GEMMASCOPE-RES-16K
    11. 9482
    Prev
    Next
    INDEX
    Explanations

    phrases related to graduation and educational milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     souci
    -0.38
     vVar
    -0.36
     tercio
    -0.35
     zwy
    -0.35
     umum
    -0.34
     nemlig
    -0.34
     nią
    -0.34
     alike
    -0.34
     mężczy
    -0.33
     wyg
    -0.33
    POSITIVE LOGITS
     Gradu
    0.86
     Graduates
    0.82
     gradient
    0.82
     gradu
    0.80
    Graduation
    0.77
     graduation
    0.76
     graduates
    0.75
     Gradient
    0.75
     calibration
    0.74
     increment
    0.74
    Activations Density 0.188%

    No Known Activations