© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 14487
    Prev
    Next
    INDEX
    Explanations

    terms related to saturation levels and their variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Satellite
    -0.88
     satellite
    -0.87
     satellites
    -0.75
    satellite
    -0.73
    rigger
    -0.72
    Satellite
    -0.71
     Sidebar
    -0.67
    blanc
    -0.66
    DateTimeField
    -0.65
     obst
    -0.65
    POSITIVE LOGITS
     sat
    1.45
     Sat
    1.36
    Sat
    1.29
     SAT
    1.25
    SAT
    1.16
     satur
    1.14
    sat
    1.10
     saturated
    1.07
    saturated
    0.97
     saturation
    0.93
    Activations Density 0.073%

    No Known Activations