© 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. 11924
    Prev
    Next
    INDEX
    Explanations

    variations of the word "hard."

    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
    omitempty
    -0.50
     ✭✭
    -0.48
    WaitGroup
    -0.42
    writeFieldEnd
    -0.40
    Soorten
    -0.39
    TagMode
    -0.38
    AutoresizingMask
    -0.36
     sumpay
    -0.35
     bellezza
    -0.35
     Jambi
    -0.35
    POSITIVE LOGITS
    wired
    0.80
    boiled
    0.71
    fought
    0.71
     fought
    0.70
     core
    0.66
    earned
    0.64
    hitting
    0.63
     pressed
    0.63
     earned
    0.63
    pressed
    0.61
    Activations Density 0.174%

    No Known Activations