© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14511
    Prev
    Next
    INDEX
    Explanations

    terms related to economic policies and financial regulations

    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
     intStringLen
    -0.31
     encant
    -0.31
     pria
    -0.30
     Geheim
    -0.29
     Auftrag
    -0.29
    дю
    -0.28
     rotina
    -0.28
    andExpect
    -0.27
     gekle
    -0.26
     configurações
    -0.26
    POSITIVE LOGITS
     subsidies
    1.09
     subsidy
    1.08
     incentives
    1.04
     relief
    1.00
     subsid
    0.99
     grants
    0.96
     scheme
    0.93
     incentive
    0.93
     Subsid
    0.93
    subsid
    0.92
    Activations Density 0.322%

    No Known Activations