© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 99531
    Prev
    Next
    INDEX
    Explanations

    references to mass or mass measurements in a scientific context

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

    mass conservation, density, anisotropy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.52
    IndentedString
    -0.49
    elect
    -0.49
     متعلقه
    -0.48
    kozó
    -0.45
     menuItem
    -0.44
     objectForKey
    -0.44
    theore
    -0.44
    criter
    -0.44
     quaisquer
    -0.43
    POSITIVE LOGITS
     mass
    2.19
    mass
    2.00
    Mass
    1.87
     Mass
    1.87
    MASS
    1.61
     MASS
    1.57
     massa
    1.38
     masses
    1.33
     Massen
    1.28
     masse
    1.24
    Activations Density 0.014%

    No Known Activations