Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3473
    Prev
    Next
    INDEX
    Explanations

    references to desert environments and their related challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     bambú
    -0.37
     répertoire
    -0.33
     geprek
    -0.33
     Klä
    -0.32
     intptr
    -0.31
    Skocz
    -0.31
    Przypisy
    -0.30
     ماز
    -0.29
     limpa
    -0.29
     εκ
    -0.29
    POSITIVE LOGITS
     Desert
    0.97
     desert
    0.95
    Desert
    0.90
    desert
    0.87
    沙漠
    0.76
    🏜
    0.74
     deserto
    0.72
     Tucson
    0.70
    Tucson
    0.70
     deserts
    0.67
    Activations Density 0.194%

    No Known Activations