© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 20-GEMMASCOPE-RES-16K
    11. 8176
    Prev
    Next
    INDEX
    Explanations

    terms related to cloud seeding and rain enhancement initiatives

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

    references to Middle Eastern countries, particularly the UAE (United Arab Emirates) and related government officials, policies, and geographical features.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    MessageTagHelper
    -0.55
     getItemCount
    -0.48
     kasarigan
    -0.45
    peq
    -0.44
     paix
    -0.43
    日閲覧
    -0.43
     ruinas
    -0.43
    onAttach
    -0.43
    BeginContext
    -0.42
    addCriterion
    -0.42
    POSITIVE LOGITS
     Dubai
    0.84
     Dhabi
    0.82
     Qatar
    0.73
     Saudi
    0.73
    Dubai
    0.69
     Kuwait
    0.67
     dubai
    0.66
     UAE
    0.63
     Doha
    0.60
    dubai
    0.59
    Activations Density 0.052%

    No Known Activations