© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 16098
    Prev
    Next
    INDEX
    Explanations

    data related to demographic and health measurements in clinical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.95
     and
    -0.58
    الحياه
    -0.56
     the
    -0.51
     a
    -0.49
    .
    -0.48
    Biographie
    -0.48
    ).
    -0.45
     "
    -0.44
    abestanden
    -0.42
    POSITIVE LOGITS
    Personendaten
    0.91
     initComponents
    0.88
     kasarigan
    0.82
    Carriera
    0.81
    DrawerToggle
    0.81
     Efq
    0.77
    awtextra
    0.76
    TestingModule
    0.75
     Shakspeare
    0.75
     Shaksp
    0.72
    Activations Density 0.741%

    No Known Activations