© 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. 22-GEMMASCOPE-RES-16K
    11. 11968
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and connections

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    execSQL
    -0.46
    تقاوى
    -0.45
    )_/¯
    -0.44
    stalt
    -0.43
    tagext
    -0.42
     ſt
    -0.41
    ftant
    -0.40
    OrBuilder
    -0.40
    ligh
    -0.40
    зопас
    -0.40
    POSITIVE LOGITS
     MainAxisSize
    0.55
     colleagues
    0.47
    UnusedPrivate
    0.46
     sister
    0.45
     Mitarbeit
    0.45
     يتيمه
    0.44
     collègues
    0.44
     colleague
    0.44
     japonaise
    0.43
     Schwester
    0.43
    Activations Density 0.203%

    No Known Activations