© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 16056
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental and ecological land use classifications

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

    Landscapes and land types

    np_acts-logits-general · gemini-2.0-flash

    natural landscapes and rural areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaynağından
    -0.52
    Personendaten
    -0.50
     čia
    -0.47
    )}>
    -0.45
     כה
    -0.43
    solicited
    -0.42
     CURLOPT
    -0.42
     verbo
    -0.41
    Closest
    -0.41
     []:
    -0.41
    POSITIVE LOGITS
     farmland
    1.21
     countryside
    1.20
     fields
    1.20
     grassland
    1.15
     forests
    1.15
     grasslands
    1.12
     forested
    1.10
     plains
    1.07
     meadows
    1.07
     grassy
    1.02
    Activations Density 0.306%

    No Known Activations