© 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. 31-GEMMASCOPE-RES-16K
    11. 11762
    Prev
    Next
    INDEX
    Explanations

    words related to the word "Tra" and its variations, often in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The neuron detects the word fragment "tra" at the beginning of words like "trabecular," "traditional," "trajectories," and "trametes."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "Tram" or words beginning with "Tra" that are part of scientific or technical terminology.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    риев
    -0.39
     Audiodateien
    -0.35
    GEBURTSDATUM
    -0.35
     InputDecoration
    -0.34
    igkeit
    -0.33
    complexType
    -0.32
    intenant
    -0.31
     Oli
    -0.30
     AP
    -0.29
    enumi
    -0.29
    POSITIVE LOGITS
     tra
    0.77
     Tra
    0.71
    LabelTagHelper
    0.65
     Тра
    0.64
    tra
    0.64
    Tra
    0.61
     тра
    0.60
     AssemblyCulture
    0.59
    traj
    0.59
    monary
    0.57
    Activations Density 0.104%

    No Known Activations