© 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. 2-GEMMASCOPE-RES-16K
    11. 3537
    Prev
    Next
    INDEX
    Explanations

    repeated use of the word "primarily" to indicate focus on dominant themes or elements

    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
    ThroughAttribute
    -0.73
    ⓧ
    -0.63
    Datuak
    -0.61
    ItemBackground
    -0.55
    ImageContext
    -0.55
    ctez
    -0.52
    ighbor
    -0.52
    ArgsConstructor
    -0.50
    nloa
    -0.49
     препратки
    -0.48
    POSITIVE LOGITS
     primarily
    2.09
    primarily
    1.86
     Primarily
    1.77
     predominantly
    1.73
     mainly
    1.70
     principally
    1.59
     chiefly
    1.58
     Mainly
    1.57
    mainly
    1.46
    Mainly
    1.44
    Activations Density 0.120%

    No Known Activations