© 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 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. 20425
    Prev
    Next
    INDEX
    Explanations

    references to the word "lime" and its variations, as well as mentions of "dime" and words related to rhyming

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

    lime, dime novels, rhyme

    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
    ruiter
    -0.46
     Stor
    -0.46
    andr
    -0.46
    suzuki
    -0.45
     Capt
    -0.44
    arwal
    -0.44
     Ballard
    -0.44
     Navarra
    -0.44
    student
    -0.44
    สือ
    -0.43
    POSITIVE LOGITS
    Lime
    1.22
     Lime
    1.17
    lime
    1.06
     lime
    1.04
     limes
    0.74
    ライム
    0.70
    Slime
    0.66
     Wikiseite
    0.63
     Slime
    0.62
    IME
    0.57
    Activations Density 0.004%

    No Known Activations