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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7506
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "li" related to a medical context

    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
     ujednoznacz
    -0.59
     Chwiliwch
    -0.49
    onOptions
    -0.48
     VIDEOTAPE
    -0.47
     ब्रेकडाउन
    -0.45
    новниш
    -0.44
     Wicidata
    -0.43
     للمعارف
    -0.43
     independently
    -0.42
    Rhestr
    -0.42
    POSITIVE LOGITS
     تعدى
    0.38
    DrawerToggle
    0.36
    ({_
    0.35
    分か
    0.34
    Distribuzione
    0.34
    Hentet
    0.33
     GenerationType
    0.33
    สือ
    0.32
    minal
    0.32
    queurs
    0.32
    Activations Density 0.283%

    No Known Activations