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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 2726
    Prev
    Next
    INDEX
    Explanations

    references to contemporary themes and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bebasan
    -0.77
    setof
    -0.76
    り
    -0.64
     Rass
    -0.63
     nucleus
    -0.63
     lahan
    -0.63
    "):
    
    -0.63
    scrollView
    -0.62
     Schweitzer
    -0.62
    Rudy
    -0.62
    POSITIVE LOGITS
     contemporain
    1.18
     Contemporary
    1.16
    Contemporary
    1.07
     contemporánea
    1.04
     CONTEM
    1.03
     contemporaine
    1.02
     contemporáneo
    0.98
    contemporary
    0.96
     contemporary
    0.93
     contempor
    0.92
    Activations Density 0.108%

    No Known Activations