© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 9091
    Prev
    Next
    INDEX
    Explanations

    references to personal identities and the roles individuals play in different contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    CrossRef
    -0.47
     يتيمه
    -0.43
    Rujuakan
    -0.42
    ismet
    -0.41
    aiso
    -0.39
    OPTIONAL
    -0.38
    itoneal
    -0.38
    괜
    -0.38
     OPTIONAL
    -0.37
    icose
    -0.37
    POSITIVE LOGITS
     cannot
    2.95
    cannot
    2.47
     Cannot
    2.34
    Cannot
    2.20
     couldn
    2.16
     unable
    2.08
     cant
    2.02
     CANNOT
    1.99
     нельзя
    1.88
     Unable
    1.81
    Activations Density 1.643%

    No Known Activations