© 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. 34-GEMMASCOPE-RES-16K
    11. 4279
    Prev
    Next
    INDEX
    Explanations

    actions and sequences related to intent and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     awalnya
    -0.61
     wcześ
    -0.59
     vooraf
    -0.59
     wcześniej
    -0.58
     daardoor
    -0.56
     sengaja
    -0.56
     daarvoor
    -0.54
     hierbei
    -0.52
     eerder
    -0.52
     kiedyś
    -0.52
    POSITIVE LOGITS
     proceeded
    1.27
     proceed
    1.26
    proceed
    1.09
     proceeding
    1.05
     proceeds
    1.04
     Proceed
    1.03
     PROCEED
    0.97
     procede
    0.96
    Proceed
    0.94
     Proceeding
    0.87
    Activations Density 0.798%

    No Known Activations