© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 6835
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mass" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sphinct
    -0.64
     Needles
    -0.63
    FormTagHelper
    -0.58
    ">//
    -0.56
     ChromeDriver
    -0.56
    imdi
    -0.56
     Wohnen
    -0.54
     Refrigerator
    -0.52
     Bernadette
    -0.52
     Veneto
    -0.51
    POSITIVE LOGITS
     Mass
    0.95
    Mass
    0.88
    achusetts
    0.83
     Massen
    0.82
    MASS
    0.78
     MASS
    0.77
     mass
    0.74
     Mas
    0.74
    fastjson
    0.71
     masse
    0.71
    Activations Density 0.086%

    No Known Activations