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. 92632
    Prev
    Next
    INDEX
    Explanations

    SQL query components and operations involving data retrieval

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

    existing user

    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
    httphttps
    -0.73
     queſta
    -0.72
    出版年
    -0.71
    évaluateur
    -0.67
    bootstrapcdn
    -0.63
    BibitemShut
    -0.62
    WebServlet
    -0.61
    Ӕ
    -0.60
    باردا
    -0.59
     kasarigan
    -0.57
    POSITIVE LOGITS
    SharedCtor
    0.33
     answer
    0.32
     &___
    0.29
     answers
    0.29
     đáp
    0.25
    fetchone
    0.25
     deber
    0.23
     results
    0.23
     estim
    0.23
     varanda
    0.23
    Activations Density 0.021%

    No Known Activations