© 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. 10-GEMMASCOPE-RES-16K
    11. 7025
    Prev
    Next
    INDEX
    Explanations

    instances of the word "being" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Karsten
    -0.85
    protoc
    -0.78
    </b>
    -0.77
    cda
    -0.76
     Crot
    -0.76
    addContainerGap
    -0.74
    <b>
    -0.73
     Rhi
    -0.73
     Faw
    -0.73
     Conley
    -0.73
    POSITIVE LOGITS
     BEING
    0.92
     Being
    0.84
     being
    0.82
    бенок
    0.77
    Being
    0.76
    FieldBuilder
    0.76
    ness
    0.76
    ieteur
    0.75
    being
    0.71
     Bein
    0.68
    Activations Density 0.121%

    No Known Activations