© 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. 41-GEMMASCOPE-RES-16K
    6. 7984
    Prev
    Next
    INDEX
    Explanations

    technical terms and rules related to physics and mathematics, especially those involving differentiation and price dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.48
    Diwedd
    -0.47
    PerformLayout
    -0.40
    
    -0.39
    EndInit
    -0.37
     terecht
    -0.37
    lccn
    -0.37
     '\\;'
    -0.36
    podium
    -0.35
    ISupport
    -0.34
    POSITIVE LOGITS
     rule
    3.66
     rules
    3.42
     Rule
    3.20
    rule
    3.20
    Rule
    3.09
     Rules
    3.06
    rules
    3.02
     RULE
    2.95
    Rules
    2.92
     RULES
    2.83
    Activations Density 1.023%

    No Known Activations