© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7912
    Prev
    Next
    INDEX
    Explanations

    patterns in visual representations or layouts, particularly related to data charts or graphs

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

    Delimiters or separators

    np_acts-logits-general · gemini-2.0-flash

    separators and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    =$?
    -0.86
     */
    -0.73
    !")
    -0.70
    jspx
    -0.66
    تقاوى
    -0.66
     ""],
    -0.66
    PMailer
    -0.65
    !';
    -0.64
    BeginInit
    -0.64
    $")
    -0.64
    POSITIVE LOGITS
     o
    0.61
    PARATOR
    0.59
     `
    0.54
           
    0.53
          
    0.53
     /
    0.53
            
    0.52
         
    0.52
     |
    0.51
    主人
    0.51
    Activations Density 0.482%

    No Known Activations