© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4957
    Prev
    Next
    INDEX
    Explanations

    instances of the word "expressed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.61
     breath
    -0.58
    GeoNames
    -0.57
    intégr
    -0.57
    NamedQuery
    -0.56
    HtmlAttribute
    -0.55
    colleg
    -0.54
     "..\..\
    -0.53
     Legge
    -0.53
     Zha
    -0.53
    POSITIVE LOGITS
     expressed
    1.21
    expressed
    1.01
     expressing
    0.82
    Děkuji
    0.74
     expresó
    0.72
    openhauer
    0.72
     expresar
    0.68
    Према
    0.68
     expresses
    0.67
    íslu
    0.66
    Activations Density 0.043%

    No Known Activations