© 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. 3-GEMMASCOPE-RES-16K
    11. 6105
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "heavy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.66
     autorytatywna
    -0.60
    ifrance
    -0.47
    
    -0.47
     viewType
    -0.45
     volume
    -0.44
     volumes
    -0.44
     VOLUME
    -0.43
     Volume
    -0.43
     AppBundle
    -0.43
    POSITIVE LOGITS
     Heavy
    0.98
     heavy
    0.97
    Heavy
    0.93
    heavy
    0.88
     HEAVY
    0.78
     heavier
    0.70
     heaviest
    0.69
     Tell
    0.68
    重
    0.68
     тяже
    0.60
    Activations Density 0.029%

    No Known Activations