© 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 EvalsExportsinterp-engineNEWAPI 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. 112066
    Prev
    Next
    INDEX
    Explanations

    terms related to public transportation systems and infrastructure

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

    subway, metro, and underground lines

    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
     AssemblyTitle
    -0.70
    jsxFileName
    -0.58
    CDCl
    -0.50
    robial
    -0.49
     >=",
    -0.48
    tificate
    -0.47
    GRANTED
    -0.47
    illoma
    -0.47
    LabelTagHelper
    -0.47
    SharedDtor
    -0.47
    POSITIVE LOGITS
     subway
    0.95
     Subway
    0.80
     underground
    0.73
    Subway
    0.72
     metro
    0.60
     métro
    0.60
     Underground
    0.59
     метро
    0.56
    Underground
    0.55
    地下鉄
    0.54
    Activations Density 0.003%

    No Known Activations