© 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. 4291
    Prev
    Next
    INDEX
    Explanations

    the name "Kevin" and related mentions in the text

    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
    esri
    -0.83
     Clue
    -0.79
    +#+#
    -0.79
    WSGI
    -0.77
     propOrder
    -0.77
     bezeichneter
    -0.77
    ahashi
    -0.74
     ComVisible
    -0.74
    cination
    -0.73
     Roku
    -0.71
    POSITIVE LOGITS
     dat
    0.86
     Dat
    0.81
     Carl
    0.77
     AB
    0.76
    Dat
    0.73
     Kevin
    0.72
    LikeLike
    0.70
     ST
    0.70
     gloves
    0.68
     Tuf
    0.65
    Activations Density 0.087%

    No Known Activations