© 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. 104357
    Prev
    Next
    INDEX
    Explanations

    references to the city of Washington, D.C

    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
     createSlice
    -0.54
     elif
    -0.48
     мәкалә
    -0.47
    enumii
    -0.44
    omitempty
    -0.44
    Personensuche
    -0.43
     parseFrom
    -0.41
    oredCriteria
    -0.41
    PreferredItem
    -0.41
     protoimpl
    -0.41
    POSITIVE LOGITS
     Washington
    1.23
    Washington
    1.10
     washington
    1.00
     WASHINGTON
    0.96
     Washing
    0.92
    WASHINGTON
    0.86
    washington
    0.85
     Wash
    0.75
    ASHINGTON
    0.73
    Washing
    0.73
    Activations Density 0.009%

    No Known Activations