© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 66131
    Prev
    Next
    INDEX
    Explanations

    the keyword "word" in various contexts related to its usage and frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    word lines or contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    -0.64
     Leth
    -0.52
     $\{\
    -0.51
     I
    -0.50
     meagre
    -0.50
     Lonely
    -0.49
     Minim
    -0.49
    ilia
    -0.48
     Cull
    -0.48
    cui
    -0.48
    POSITIVE LOGITS
    Word
    1.21
     Word
    1.15
     word
    1.12
     WORD
    1.09
    WORD
    1.02
    word
    1.01
     WORDS
    0.90
    Words
    0.89
     Words
    0.87
     words
    0.85
    Activations Density 0.013%

    No Known Activations