© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 7513
    Prev
    Next
    INDEX
    Explanations

    financial and legal terms or references in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.95
    GEBURTSDATUM
    -0.91
     unknownFields
    -0.87
    ContentAsync
    -0.86
     esternos
    -0.84
    KommentareTeilen
    -0.83
     Efq
    -0.80
    TestingModule
    -0.79
     fieldNum
    -0.79
    rouvez
    -0.76
    POSITIVE LOGITS
     according
    1.15
    according
    0.86
     said
    0.81
    According
    0.72
     según
    0.71
    said
    0.65
     officials
    0.64
     selon
    0.63
     menurut
    0.61
     he
    0.61
    Activations Density 0.123%

    No Known Activations