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. 19-GEMMASCOPE-RES-16K
    6. 4384
    Prev
    Next
    INDEX
    Explanations

    elements related to memorials and historical monuments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.81
    
    -0.65
    AddTagHelper
    -0.59
    évaluateur
    -0.57
    Искәрмәләр
    -0.57
     Delia
    -0.54
     clove
    -0.52
     nahilalakip
    -0.52
     racket
    -0.52
     שוליים
    -0.52
    POSITIVE LOGITS
     statue
    1.78
     sculpture
    1.58
     monument
    1.58
     statues
    1.53
     sculptures
    1.37
    statue
    1.35
     Monument
    1.33
     Statue
    1.32
     monuments
    1.30
     Sculpture
    1.28
    Activations Density 0.196%

    No Known Activations