© 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. 31-GEMMASCOPE-RES-131K
    11. 23769
    Prev
    Next
    INDEX
    Explanations

    references to various online trading platforms and their features

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

    online platforms and store hosting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     يتيمه
    -0.65
    GOTREF
    -0.61
     disambiguazione
    -0.57
    setVerticalGroup
    -0.56
    SequentialGroup
    -0.52
    ScopeManager
    -0.49
    ConstraintMaker
    -0.49
    RegressionTest
    -0.47
    исленность
    -0.46
     MainAxisSize
    -0.45
    POSITIVE LOGITS
     platform
    2.89
    platform
    2.45
     platforms
    2.41
     Platform
    2.33
     plataforma
    2.31
    Platform
    2.23
    平台
    2.17
     Plattform
    2.17
     PLATFORM
    2.14
     piattaforma
    2.08
    Activations Density 0.168%

    No Known Activations