© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 9783
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to electrical components and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.47
    roll
    -0.39
    ädie
    -0.38
     Waray
    -0.38
     تضيفلها
    -0.37
    엡
    -0.37
     roll
    -0.36
     Younger
    -0.35
    KURZBESCHREIBUNG
    -0.35
    췄
    -0.35
    POSITIVE LOGITS
     currents
    1.17
     Current
    1.09
     Currents
    1.07
     current
    1.07
    Current
    1.05
    currents
    1.03
     resistance
    0.99
    current
    0.99
     corriente
    0.99
    电流
    0.98
    Activations Density 0.627%

    No Known Activations