© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8801
    Prev
    Next
    INDEX
    Explanations

    references to the economy and economic discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    absolute
    -0.46
     absol
    -0.45
     ComVisible
    -0.44
    Absolute
    -0.43
     absolute
    -0.43
     absoluto
    -0.42
     absolu
    -0.40
     Absolute
    -0.39
     abs
    -0.39
     ABSOL
    -0.38
    POSITIVE LOGITS
     economy
    1.18
     ECONOMY
    1.09
     Economy
    1.09
    economy
    1.03
    Economy
    0.98
    Environment
    0.73
     strategies
    0.70
     Environment
    0.70
    Strategy
    0.68
    strategies
    0.67
    Activations Density 0.099%

    No Known Activations