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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5392
    Prev
    Next
    INDEX
    Explanations

    terms related to mass and collective quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ︎
    -0.93
     Veneto
    -0.77
    InputTagHelper
    -0.73
     Condi
    -0.71
     Viter
    -0.70
    LEncoder
    -0.69
     subjec
    -0.69
    theless
    -0.68
     Ceci
    -0.67
     Ronde
    -0.67
    POSITIVE LOGITS
     Mass
    1.15
     MASS
    1.12
    MASS
    1.11
     mass
    1.03
    Mass
    1.00
     masses
    0.95
     Massa
    0.91
    mass
    0.89
    masses
    0.86
     Masses
    0.83
    Activations Density 0.082%

    No Known Activations