© 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. 33-GEMMASCOPE-RES-16K
    11. 12985
    Prev
    Next
    INDEX
    Explanations

    cooking-related actions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initView
    -0.41
    WithIdentifier
    -0.39
     porcentual
    -0.37
     fér
    -0.37
     cellspacing
    -0.36
     trypsin
    -0.36
     periodi
    -0.36
     initData
    -0.35
    talent
    -0.35
     kvm
    -0.35
    POSITIVE LOGITS
     visibly
    0.64
     firm
    0.54
     deseado
    0.53
    desired
    0.52
     desired
    0.52
     consistency
    0.50
     mengeluarkan
    0.49
     tamamen
    0.48
    firm
    0.46
     fully
    0.46
    Activations Density 0.218%

    No Known Activations