© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 14266
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental impacts and their effects on health and ecosystems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oneofs
    -0.50
    tagHelperRunner
    -0.49
    MigrationBuilder
    -0.48
    MLLoader
    -0.42
    ⟬
    -0.41
    protoimpl
    -0.40
    enterOuterAlt
    -0.38
    antası
    -0.37
    isContained
    -0.37
    utilisons
    -0.36
    POSITIVE LOGITS
     environment
    3.41
     Environment
    2.97
    environment
    2.95
    Environment
    2.86
     environments
    2.77
     environmental
    2.75
    環境
    2.72
    环境
    2.70
     ENVIRONMENT
    2.67
     environnement
    2.66
    Activations Density 0.822%

    No Known Activations