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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6774
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases about vehicle design and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     crappy
    -0.83
     horrible
    -0.81
     stinks
    -0.78
     shitty
    -0.77
     cheaply
    -0.77
     horrid
    -0.74
     nasty
    -0.72
     horrendous
    -0.71
     idiotic
    -0.69
     suicidal
    -0.69
    POSITIVE LOGITS
     timeless
    1.00
     elegance
    0.81
    Inspired
    0.76
     redefined
    0.75
     embodies
    0.73
     inspired
    0.73
     exquisite
    0.72
     elegant
    0.72
     inspiration
    0.70
     reinterpret
    0.70
    Activations Density 0.194%

    No Known Activations