© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105035
    Prev
    Next
    INDEX
    Explanations

    references to specific parts or sections within a text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Datuak
    -0.60
     surla
    -0.54
    assertRaises
    -0.50
    DeleteBehavior
    -0.48
    Geplaatst
    -0.43
    LEncoder
    -0.42
    AntiForgeryToken
    -0.42
     HttpStatusCode
    -0.41
    MemoryWarning
    -0.41
    HasForeignKey
    -0.41
    POSITIVE LOGITS
     parts
    1.20
     part
    1.18
    part
    1.09
    Part
    1.08
     Parts
    1.08
     PARTS
    1.05
    Parts
    1.02
     Part
    1.02
     Teile
    1.01
     parte
    0.99
    Activations Density 0.043%

    No Known Activations