© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1332
    Prev
    Next
    INDEX
    Explanations

    phrases related to urban wandering and exploration

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

    elements associated with exploring and experiencing historical or cultural locations

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

    wandering or roaming in streets

    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
     kasarigan
    -0.78
     EconPapers
    -0.73
    vician
    -0.69
    TagMode
    -0.69
    ukone
    -0.65
    aarrggbb
    -0.64
     متعلقه
    -0.63
    iencias
    -0.60
    URLException
    -0.60
     propOrder
    -0.59
    POSITIVE LOGITS
     streets
    1.64
     roads
    1.22
    streets
    1.14
     Streets
    1.13
    Streets
    0.99
     ruas
    0.94
     calles
    0.93
     STRE
    0.92
     roadways
    0.90
     strade
    0.89
    Activations Density 0.118%

    No Known Activations