© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12472
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "Kar"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thống
    -0.34
     nonUne
    -0.32
    苗
    -0.32
    itness
    -0.30
     Surabaya
    -0.29
     squeak
    -0.29
    blusa
    -0.28
    mbros
    -0.27
     Steg
    -0.27
     Clown
    -0.26
    POSITIVE LOGITS
    Kar
    2.17
     Kar
    2.17
     kar
    2.14
     KAR
    2.13
    kar
    2.06
    KAR
    2.05
     CAR
    1.91
    CAR
    1.84
     carb
    1.78
     Carb
    1.76
    Activations Density 0.365%

    No Known Activations