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. 3-GEMMASCOPE-RES-16K
    6. 10976
    Prev
    Next
    INDEX
    Explanations

    references to machine learning and related metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.90
     Baillargeon
    -0.89
     doInBackground
    -0.87
     Coven
    -0.74
    WaitGroup
    -0.74
     Magdal
    -0.73
    +#+#
    -0.70
    Portail
    -0.67
     Infórmanos
    -0.67
    bbons
    -0.64
    POSITIVE LOGITS
    ml
    2.96
     ml
    2.71
    ML
    2.64
     ML
    2.54
     mL
    1.82
    mL
    1.72
     Ml
    1.59
    Ml
    1.55
    mls
    1.45
     мл
    1.34
    Activations Density 0.110%

    No Known Activations