© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 36788
    Prev
    Next
    INDEX
    Explanations

    scientific technical terms and concepts related to energy, nuclear science, and particle physics

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

    energy sciences, runaway fusion, JET, DREAM, conditioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.60
     ArrayAdapter
    -0.54
    URLException
    -0.49
     BoxFit
    -0.49
    prepareStatement
    -0.47
     feroit
    -0.45
    Personensuche
    -0.44
    例文
    -0.43
     pouvoit
    -0.42
     sumpay
    -0.42
    POSITIVE LOGITS
     pest
    0.43
    ตร์
    0.38
    atieve
    0.37
     giu
    0.36
    lasma
    0.36
     rospy
    0.36
    IMUM
    0.36
    astrar
    0.36
    исленность
    0.36
     разобра
    0.35
    Activations Density 0.035%

    No Known Activations