© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6647
    Prev
    Next
    INDEX
    Explanations

    references to deserts and their characteristics

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

    deserts

    np_acts-logits-general · gemini-2.0-flash

    Sahara, desert, arid lands

    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
     Penang
    -0.51
    TreeNode
    -0.49
     zebrafish
    -0.49
    tagHelperRunner
    -0.49
     Litu
    -0.49
     Baillargeon
    -0.48
     Woods
    -0.48
     Aceh
    -0.48
    Squirrel
    -0.47
     Vanuatu
    -0.47
    POSITIVE LOGITS
     desert
    1.46
     Desert
    1.39
    Desert
    1.33
    desert
    1.30
     deserts
    1.16
     désert
    1.11
     deserto
    1.09
     desierto
    1.09
    🌵
    1.06
    沙漠
    1.05
    Activations Density 0.268%

    No Known Activations