© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106005
    Prev
    Next
    INDEX
    Explanations

    numerical values and punctuation marks

    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
     tangan
    -0.29
    Protobuf
    -0.28
    subequations
    -0.28
     inf
    -0.28
     inspired
    -0.27
     Klick
    -0.27
    postmedia
    -0.26
     hands
    -0.26
    <code>
    -0.26
     contrasts
    -0.25
    POSITIVE LOGITS
     ExecuteAsync
    0.77
    featureID
    0.69
    RegressionTest
    0.67
     AssemblyCompany
    0.65
    posedge
    0.62
    webElementGuid
    0.60
     MainAxisSize
    0.60
    awaiter
    0.59
    providedIn
    0.59
     queſta
    0.59
    Activations Density 0.031%

    No Known Activations