© 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. 104915
    Prev
    Next
    INDEX
    Explanations

    specific designations or identifiers, such as names and codes within structured data

    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
     Económica
    -0.44
     Penge
    -0.42
     lentejuelas
    -0.41
     cumplido
    -0.40
     dignidad
    -0.40
     Kindes
    -0.40
    írus
    -0.40
     remplir
    -0.40
     voeren
    -0.40
     niña
    -0.39
    POSITIVE LOGITS
     AssemblyVersion
    0.51
    IBOutlet
    0.51
    RTSN
    0.50
     IBOutlet
    0.48
     ContentValues
    0.47
    UserScript
    0.47
     ModelRenderer
    0.46
    elemField
    0.46
     zwiſchen
    0.46
     Walkover
    0.45
    Activations Density 0.111%

    No Known Activations