© 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. 22-GEMMASCOPE-RES-16K
    11. 8839
    Prev
    Next
    INDEX
    Explanations

    various forms and mentions of the word "word"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clifton
    -0.51
    IANI
    -0.44
     Hau
    -0.44
    สัง
    -0.43
     McAllister
    -0.42
    ilaire
    -0.42
    Allister
    -0.42
     Huber
    -0.42
     realising
    -0.41
     Osorio
    -0.41
    POSITIVE LOGITS
     word
    1.13
    Word
    1.11
     WORD
    1.08
     Word
    1.07
     words
    1.01
    Words
    0.98
    WORD
    0.96
     WORDS
    0.95
     Words
    0.95
    word
    0.94
    Activations Density 0.131%

    No Known Activations