© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6230
    Prev
    Next
    INDEX
    Explanations

    references to the term "Cab" in various contexts

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

    "Cab", "Kab", or "CAB"

    np_acts-logits-general · gemini-2.0-flash

    Cab and Kab starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ]='\
    -0.70
    kuuta
    -0.68
    pyplot
    -0.62
     Sequo
    -0.61
     Cera
    -0.61
    Barium
    -0.61
    ----</
    -0.60
     Bourgoin
    -0.60
    thâu
    -0.60
     TType
    -0.59
    POSITIVE LOGITS
     MessageBoxIcon
    0.67
     Kab
    0.60
     kab
    0.56
    Kab
    0.51
    SequentialGroup
    0.51
     Cab
    0.50
     Cabral
    0.49
     CAB
    0.49
    elemField
    0.48
    первых
    0.47
    Activations Density 0.124%

    No Known Activations