© 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. 3-GEMMASCOPE-RES-16K
    11. 10423
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "li" potentially in various contexts, particularly in code snippets or data-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italijani
    -0.61
     propOrder
    -0.60
    󠁿
    -0.57
    دانشنامهٔ
    -0.56
    LEncoder
    -0.55
    transQ
    -0.55
    featureID
    -0.52
     CommonModule
    -0.50
    InputBorder
    -0.50
    ſicht
    -0.49
    POSITIVE LOGITS
     li
    0.78
     ri
    0.62
     ru
    0.58
     stat
    0.47
     definite
    0.46
    lich
    0.45
    tick
    0.44
    stat
    0.42
     sou
    0.42
     curtain
    0.41
    Activations Density 1.376%

    No Known Activations