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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120159
    Prev
    Next
    INDEX
    Explanations

    elements of programming and software libraries, particularly in relation to definitions, imports, and configurations

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

    apache commons luatex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     AssemblyCompany
    -0.51
     ویکی‌پدی
    -0.47
     Мексичка
    -0.45
    principalTable
    -0.43
    <eos>
    -0.32
     betweenstory
    -0.29
    [
    -0.29
    sidemargin
    -0.29
     entonces
    -0.28
    retweeted
    -0.28
    POSITIVE LOGITS
    niſſe
    0.71
     zwiſchen
    0.71
    <unused41>
    0.71
    <unused3>
    0.70
     ſondern
    0.70
    <unused23>
    0.70
    <unused42>
    0.70
    <unused14>
    0.70
    [@BOS@]
    0.70
    <unused8>
    0.70
    Activations Density 0.122%

    No Known Activations