© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103738
    Prev
    Next
    INDEX
    Explanations

    statistical data presentation and formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    InstrumentedTest
    -0.36
    rollment
    -0.34
     Савезне
    -0.32
    ようになります
    -0.32
     BrowserModule
    -0.32
     useAuth
    -0.31
    ことはありません
    -0.31
    LookAnd
    -0.30
    hoeddwyd
    -0.30
     setCode
    -0.29
    POSITIVE LOGITS
    colhead
    0.49
    astéroïdes
    0.49
    IVEREF
    0.49
    urry
    0.48
    Życiorys
    0.47
     Myron
    0.47
     gereken
    0.46
    rawy
    0.46
     لينك
    0.45
    ruptedException
    0.44
    Activations Density 0.107%

    No Known Activations