© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 45380
    Prev
    Next
    INDEX
    Explanations

    references to programming libraries or frameworks in code-related contexts

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

    Gson, Vulkan, Android ImageView

    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
     createState
    -0.45
    تقاوى
    -0.43
     disambiguazione
    -0.35
    исленность
    -0.34
    Portail
    -0.33
    Lig
    -0.32
    Derbyniad
    -0.31
    }{*}{
    -0.30
    はじめに
    -0.30
    [](
    -0.29
    POSITIVE LOGITS
     SQLException
    3.97
     JSONException
    1.05
    prepareStatement
    1.05
     RemoteException
    1.03
     IOException
    0.97
    SQLException
    0.85
     SqlCommand
    0.82
    executeQuery
    0.78
    ruptedException
    0.75
     SqlConnection
    0.74
    Activations Density 0.000%

    No Known Activations