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. 16-GEMMASCOPE-RES-16K
    6. 12694
    Prev
    Next
    INDEX
    Explanations

    technical terms and notations related to programming and mathematics

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

    Code or paths containing "lib", "X", "Delta", "EIS", "c", "CFS", "k", "main", "psi"

    np_acts-logits-general · gemini-2.0-flash

    technical code and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatefulWidget
    -0.77
    ollectionView
    -0.70
    зулта
    -0.70
    sprogramm
    -0.70
    AndroidJUnit
    -0.69
    )"),
    -0.68
    atrième
    -0.68
     protoimpl
    -0.68
    httphttps
    -0.68
     препратки
    -0.65
    POSITIVE LOGITS
     full
    0.39
     giras
    0.38
     outright
    0.38
     without
    0.37
    kin
    0.37
     ange
    0.37
    DISCUSSION
    0.36
    putstr
    0.36
     testified
    0.35
     بگیر
    0.35
    Activations Density 1.383%

    No Known Activations