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. 56703
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and mathematical expressions

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

    code block delimiters

    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
    .
    -0.39
     (
    -0.34
     тоже
    -0.30
    EClass
    -0.30
     =
    -0.29
    อยู่
    -0.29
     is
    -0.29
     for
    -0.28
     if
    -0.28
     while
    -0.28
    POSITIVE LOGITS
     незавершена
    1.24
    ftagPool
    1.09
    Autoritní
    1.03
    GEBURTSDATUM
    1.02
    complexContent
    1.00
    脚注の使い方
    1.00
    httphttps
    0.98
     defaultstate
    0.98
    الحياه
    0.98
     snippetHide
    0.96
    Activations Density 0.009%

    No Known Activations