© 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. 33-GEMMASCOPE-RES-16K
    11. 11301
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to taxation and fiscal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ainfi
    -0.62
    tahankan
    -0.62
     Infór
    -0.57
     âmes
    -0.57
     feroit
    -0.57
     plufieurs
    -0.56
     lámparas
    -0.56
     misalnya
    -0.55
     defaultstate
    -0.54
     Beſ
    -0.54
    POSITIVE LOGITS
    related
    0.52
     extravag
    0.48
    focused
    0.47
    -
    0.47
    izational
    0.45
    oriented
    0.44
     related
    0.43
    ButterKnife
    0.43
     chops
    0.43
     behe
    0.42
    Activations Density 2.008%

    No Known Activations