© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 230
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting used to emphasize excitement or exclamation in text

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

    Positive sentiment after punctuation

    np_acts-logits-general · gemini-2.0-flash

    sentence-ending punctuation

    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
    出版年
    -0.98
    ."],
    -0.67
     myſelf
    -0.66
     Efq
    -0.65
     Majefty
    -0.65
    dialement
    -0.62
     ſtate
    -0.62
    
    -0.61
     perſon
    -0.61
    SBATCH
    -0.61
    POSITIVE LOGITS
     yay
    1.40
     Yay
    1.29
    Yay
    1.24
    yay
    1.13
     woo
    1.10
     wow
    1.08
    YAY
    1.06
     Wow
    1.03
    wow
    0.99
    Wow
    0.99
    Activations Density 0.217%

    No Known Activations