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. 20-GEMMASCOPE-RES-16K
    6. 2397
    Prev
    Next
    INDEX
    Explanations

    issues related to healthcare reform and economic implications

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

    preceding "system" or a similar word

    np_acts-logits-general · gemini-2.0-flash

    systems

    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
    rungsseite
    -0.51
    فحة
    -0.49
    ciles
    -0.49
     actionTypes
    -0.49
    ardia
    -0.47
    клопе
    -0.47
    ipfel
    -0.47
    тар
    -0.46
    peutic
    -0.46
    出版年
    -0.44
    POSITIVE LOGITS
     system
    2.20
    system
    1.91
     sistema
    1.80
     systems
    1.79
     système
    1.76
     System
    1.70
     SYSTEM
    1.69
     systemu
    1.66
    ssystem
    1.66
     syste
    1.62
    Activations Density 0.474%

    No Known Activations