© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 9924
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking actions and steps to achieve goals or prevent issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoField
    -0.54
    ddots
    -0.54
     useHistory
    -0.54
     lands
    -0.52
     rambling
    -0.51
     orgasm
    -0.49
     Inheritance
    -0.48
    Inheritance
    -0.48
     bashing
    -0.48
     inheritance
    -0.48
    POSITIVE LOGITS
     measures
    1.06
    Measures
    1.00
     Maßnahmen
    0.95
     Measures
    0.95
    措施
    0.94
    measures
    0.94
     medidas
    0.93
     steps
    0.91
     Steps
    0.87
    steps
    0.87
    Activations Density 0.243%

    No Known Activations