© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27384
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to epigenetics

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

    words starting with Ep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.87
     transfieras
    -0.69
    roud
    -0.65
     onOptions
    -0.64
     Sucher
    -0.63
    ​​​​​​​
    -0.63
    layoutControl
    -0.62
    aip
    -0.61
     estekak
    -0.60
     XNUMX
    -0.60
    POSITIVE LOGITS
     Ep
    1.14
     ep
    1.13
     EP
    1.07
     Epif
    1.03
    ep
    1.02
     Epi
    1.00
    Ep
    1.00
    Epil
    0.99
     AssemblyTitle
    0.92
     epi
    0.89
    Activations Density 0.035%

    No Known Activations