© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 12386
    Prev
    Next
    INDEX
    Explanations

    phrases expressing intent or purpose, particularly those starting with "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dép
    -0.38
     desplie
    -0.35
     goutte
    -0.34
     considerar
    -0.33
     déploy
    -0.32
     desple
    -0.32
     suffit
    -0.31
     adoptar
    -0.31
     src
    -0.31
     Consider
    -0.31
    POSITIVE LOGITS
     distract
    0.69
     intimidate
    0.69
    IUrlHelper
    0.67
    IsContent
    0.66
     justify
    0.66
    UrlResolution
    0.65
     impress
    0.65
     punish
    0.62
     kasarigan
    0.62
     bolster
    0.60
    Activations Density 0.494%

    No Known Activations