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. 5345
    Prev
    Next
    INDEX
    Explanations

    proper names and their pronunciations

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

    followed by parenthesized alternatives

    np_acts-logits-general · gemini-2.0-flash

    alternative spellings of names

    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
     Monfieur
    -0.95
     myſelf
    -0.91
     themſelves
    -0.89
     purpoſe
    -0.85
     Efq
    -0.82
     itſelf
    -0.80
     Diſ
    -0.80
     leaſt
    -0.79
     Majefty
    -0.78
     himſelf
    -0.78
    POSITIVE LOGITS
    انجليز
    0.55
    ĕ
    0.51
    NaOH
    0.51
    bootstrapcdn
    0.49
     spelled
    0.48
    epik
    0.48
     pronouncing
    0.48
     muualla
    0.47
    uesia
    0.46
     ap
    0.46
    Activations Density 0.100%

    No Known Activations