© 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. 11-GEMMASCOPE-RES-16K
    11. 9340
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "something"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Datuak
    -0.84
    UnusedPrivate
    -0.80
     foncé
    -0.76
    zbęd
    -0.75
    owohl
    -0.73
     Lait
    -0.72
    日閲覧
    -0.72
     CEP
    -0.70
     Kays
    -0.69
    ГЛА
    -0.69
    POSITIVE LOGITS
     something
    1.64
    something
    1.58
     Something
    1.57
    Something
    1.54
     SOMETHING
    1.50
    ETHING
    1.48
    Somebody
    1.35
     somethin
    1.32
    Someone
    1.18
     else
    1.16
    Activations Density 0.066%

    No Known Activations