© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8451
    Prev
    Next
    INDEX
    Explanations

    code-related elements or structure within the text

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

    Code-related words and symbols

    np_acts-logits-general · gemini-2.0-flash

    words followed by specific punctuation or content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -1.12
     
    -0.85
     ,
    -0.81
       
    -0.79
        
    -0.61
     "
    -0.60
    -0.58
     my
    -0.58
     a
    -0.57
     .
    -0.56
    POSITIVE LOGITS
     Efq
    1.25
    
    1.23
     $_(
    1.20
    tanleria
    1.20
     $_"
    1.19
    DockStyle
    1.19
     Majefty
    1.18
    AsUp
    1.16
    ſelves
    1.15
     ―――――
    1.14
    Activations Density 1.505%

    No Known Activations