© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 2130
    Prev
    Next
    INDEX
    Explanations

    complex mathematical notation and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     geïsole
    -0.59
     nė
    -0.57
     pioggia
    -0.55
     zijne
    -0.54
     négociations
    -0.52
     veilig
    -0.52
     overras
    -0.51
     sikker
    -0.49
     koniecz
    -0.49
     negociación
    -0.49
    POSITIVE LOGITS
    ***
    1.05
    ****
    0.89
    *****
    0.84
    *)
    0.81
    *******
    0.77
     ujednoznacz
    0.73
    ********
    0.71
    ******
    0.71
    *********
    0.67
    **)
    0.67
    Activations Density 0.724%

    No Known Activations