© 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. 21-GEMMASCOPE-RES-16K
    6. 10773
    Prev
    Next
    INDEX
    Explanations

    terms related to economic concepts and conditions, particularly focusing on devaluation and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.51
    
    -0.50
    msgTypes
    -0.50
    
    -0.50
    Дерекк
    -0.50
     EconPapers
    -0.50
    ſelben
    -0.49
     تضيفلها
    -0.49
    Rhestr
    -0.49
     informée
    -0.49
    POSITIVE LOGITS
     inflation
    0.59
     price
    0.57
     prices
    0.52
     cost
    0.50
     inflación
    0.47
     inflationary
    0.47
    Inflation
    0.45
     costs
    0.42
    MessageTagHelper
    0.42
    inflation
    0.42
    Activations Density 0.179%

    No Known Activations