© 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. 41-GEMMASCOPE-RES-16K
    11. 13274
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to activities and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     вони
    -0.52
     вона
    -0.44
     endforeach
    -0.43
    seamnă
    -0.43
    bkz
    -0.43
    __':
    -0.42
     они
    -0.42
    __':
    -0.42
    それは
    -0.40
    彼は
    -0.40
    POSITIVE LOGITS
     freely
    0.81
     peacefully
    0.78
     efficiently
    0.76
     extensively
    0.76
     quietly
    0.76
     aggressively
    0.75
     everything
    0.74
     them
    0.73
     successfully
    0.72
     independently
    0.72
    Activations Density 1.300%

    No Known Activations