© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14572
    Prev
    Next
    INDEX
    Explanations

    pronouns and references to people or groups

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ➟
    -0.61
     von
    -0.46
    ci
    -0.46
     De
    -0.46
    <eos>
    -0.46
    uc
    -0.46
    cancelButton
    -0.45
     DEC
    -0.44
    dec
    -0.44
    a
    -0.44
    POSITIVE LOGITS
    ########.
    0.98
     houſe
    0.97
     Efq
    0.97
     createState
    0.95
     comigo
    0.94
     autorytatywna
    0.93
     Monfieur
    0.90
    InvalidProtocol
    0.84
     myſelf
    0.82
     ſta
    0.81
    Activations Density 0.184%

    No Known Activations