© 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. 20-GEMMASCOPE-RES-16K
    11. 9191
    Prev
    Next
    INDEX
    Explanations

    references to mass and mass-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The neuron activates for the word "mass", especially when referring to large quantities or collections of things.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.56
    AnimationsModule
    -0.51
     wireType
    -0.51
     câmera
    -0.50
     embreagem
    -0.49
     Yuen
    -0.49
    pDialog
    -0.48
    <bos>
    -0.48
     objectForKey
    -0.47
    richTextPanel
    -0.47
    POSITIVE LOGITS
    mass
    0.94
     mass
    0.93
     Mass
    0.90
    Mass
    0.88
    MASS
    0.83
     MASS
    0.81
     massa
    0.75
     Massa
    0.72
     Masses
    0.71
    sse
    0.69
    Activations Density 0.084%

    No Known Activations