© 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. 3-GEMMASCOPE-RES-16K
    11. 1079
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Paul."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -1.06
     Anſ
    -1.04
     iſt
    -1.03
     ſche
    -1.00
     Monfieur
    -0.99
     Houſe
    -0.96
     preſent
    -0.96
     Diſ
    -0.95
     purpoſe
    -0.93
     Reſ
    -0.93
    POSITIVE LOGITS
     Paul
    3.05
    Paul
    2.80
     PAUL
    2.38
     paul
    2.23
    PAUL
    2.16
    paul
    2.08
     Paulus
    1.39
     Paulson
    1.33
    ポール
    1.24
     Pau
    1.19
    Activations Density 0.050%

    No Known Activations