© 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
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 8197
    Prev
    Next
    INDEX
    Explanations

    names or terms related to "Ki" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.51
     resourceCulture
    -0.50
    saraba
    -0.50
     nahilalakip
    -0.45
    itinéraire
    -0.45
    vician
    -0.43
    RegressionTest
    -0.42
    Rujuakan
    -0.42
    Temp
    -0.40
    GTCX
    -0.40
    POSITIVE LOGITS
     Ki
    0.66
    Ki
    0.57
     KI
    0.56
     Kira
    0.56
    ismet
    0.51
     Kir
    0.49
     ki
    0.49
    romycin
    0.47
     Ки
    0.47
     KIR
    0.45
    Activations Density 0.207%

    No Known Activations