© 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. 16-GEMMASCOPE-RES-65K
    11. 28232
    Prev
    Next
    INDEX
    Explanations

    references to land and land-related categories

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

    land use and cover

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trotz
    -0.96
     myſelf
    -0.95
    >>>>>
    -0.94
     Valerio
    -0.93
     Erfurt
    -0.91
     pamph
    -0.88
     themſelves
    -0.87
     himſelf
    -0.87
    tems
    -0.87
     neceff
    -0.86
    POSITIVE LOGITS
     LAND
    1.20
     Land
    1.16
    land
    1.05
    Land
    1.04
     land
    1.02
     Landis
    0.98
    lands
    0.92
     Landry
    0.91
    LAND
    0.85
     Landon
    0.85
    Activations Density 0.021%

    No Known Activations