© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3963
    Prev
    Next
    INDEX
    Explanations

    statistical terms related to ratios or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    Not in Any Lists

    No Comments

    Negative Logits
    autaire
    -0.50
     gezet
    -0.50
    lccn
    -0.49
     aanges
    -0.48
     cuán
    -0.48
     écout
    -0.47
     geleverd
    -0.47
     leyendas
    -0.46
    Earnings
    -0.46
     ucapan
    -0.46
    POSITIVE LOGITS
     proportion
    1.44
     prop
    1.34
     proportions
    1.30
     Prop
    1.29
     proposition
    1.27
    propor
    1.27
    proportion
    1.24
     Proportion
    1.24
     Propor
    1.22
    prop
    1.20
    Activations Density 0.129%

    No Known Activations