© 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. 104379
    Prev
    Next
    INDEX
    Explanations

    elements and structures commonly associated with programming syntax and floating-point calculations

    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
     ProtoMessage
    -0.86
    WithIOException
    -0.68
    ChildScrollView
    -0.66
    zionalità
    -0.60
    FailureListener
    -0.58
    featureID
    -0.55
    ंदीखरीदारी
    -0.53
     autorytatywna
    -0.53
    ButterKnife
    -0.52
    */].
    -0.52
    POSITIVE LOGITS
     percent
    0.61
     percentage
    0.57
    percent
    0.46
    Percent
    0.43
     rate
    0.43
     percentages
    0.42
    percentage
    0.41
    PERCENT
    0.38
     Percent
    0.37
    Percentage
    0.35
    Activations Density 0.026%

    No Known Activations