© 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. 13-GEMMASCOPE-RES-16K
    11. 11427
    Prev
    Next
    INDEX
    Explanations

    references to actions involving decision-making or evaluation processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     itſelf
    -0.65
     myſelf
    -0.64
     himſelf
    -0.56
    CloseOperation
    -0.54
     ſtate
    -0.54
     chofe
    -0.52
     poffe
    -0.51
     themſelves
    -0.50
    ſelves
    -0.49
     preſent
    -0.49
    POSITIVE LOGITS
     ever
    0.41
     esfuerzos
    0.37
     opiniones
    0.35
     representado
    0.35
     tampoco
    0.34
     asesinado
    0.34
     Erziehung
    0.34
     efectiva
    0.33
     desplaz
    0.33
     esferas
    0.33
    Activations Density 0.900%

    No Known Activations