© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 29448
    Prev
    Next
    INDEX
    Explanations

    phrases related to configuration settings and options

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

    ignore version or automatically adjust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appunto
    -0.39
     murni
    -0.38
     thereon
    -0.35
     himself
    -0.33
     also
    -0.33
     today
    -0.32
     ourselves
    -0.32
     that
    -0.32
     itulah
    -0.32
     either
    -0.32
    POSITIVE LOGITS
    httphttps
    0.97
    rawDesc
    0.91
    
    0.90
    OCCURRED
    0.84
    OGND
    0.82
     мәкал
    0.81
    Personensuche
    0.81
     sumpay
    0.75
     Italijanski
    0.75
    ंदीखरीदारी
    0.74
    Activations Density 0.021%

    No Known Activations