© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 108
    Prev
    Next
    INDEX
    Explanations

    locations and street names in urban settings

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

    references to street names or intersections

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

    ordinal numbers followed by street or assembly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    +#+
    -0.72
    fjspx
    -0.69
    evos
    -0.67
    RegistryLite
    -0.64
    addContainerGap
    -0.63
     وتسجيلات
    -0.63
     sangu
    -0.60
    UAGES
    -0.59
    reportWebVitals
    -0.59
    mäß
    -0.59
    POSITIVE LOGITS
    BindView
    0.50
     Drapeau
    0.48
     defStyleAttr
    0.44
    AsUp
    0.43
     elkaar
    0.43
     Insee
    0.40
     Klein
    0.40
     entstanden
    0.40
    closePath
    0.40
     ExecuteAsync
    0.40
    Activations Density 0.025%

    No Known Activations