Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15757
    Prev
    Next
    INDEX
    Explanations

    elements related to key-value pairs in data structures, specifically in XML or JSON formats

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

    Numbers, potentially in association with other characters

    np_acts-logits-general · gemini-2.0-flash

    seven

    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
    4
    -0.74
     Fourth
    -0.65
     fourth
    -0.61
     keempat
    -0.61
     FOURTH
    -0.58
    Fourth
    -0.57
     Vier
    -0.57
    ④
    -0.55
     Four
    -0.55
     fours
    -0.54
    POSITIVE LOGITS
                        
    0.92
     seventh
    0.79
    
    0.75
    Seventh
    0.73
     seven
    0.71
    					
    0.69
    WriteTagHelper
    0.68
     متعلقه
    0.68
     Seven
    0.68
     tujuh
    0.68
    Activations Density 0.034%

    No Known Activations