© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11846
    Prev
    Next
    INDEX
    Explanations

    statistical estimation terms and models related to parameters and distributions

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

    technical or academic text discussing parameters, models, and simulations, particularly focusing on true values and data generation.

    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
     Companion
    -0.29
    XmlAccessType
    -0.29
    ập
    -0.28
     metod
    -0.27
     Symbols
    -0.27
    iores
    -0.27
     Exterior
    -0.27
     phím
    -0.27
    宫
    -0.27
    IBOutlet
    -0.26
    POSITIVE LOGITS
    
    0.80
    WriteTagHelper
    0.76
     nahilalakip
    0.70
     Infórmanos
    0.65
    әрмәләр
    0.65
    Tembelea
    0.65
     betweenstory
    0.65
    tanleria
    0.63
    AddTagHelper
    0.63
    Tikang
    0.62
    Activations Density 1.052%

    No Known Activations