Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 30763
    Prev
    Next
    INDEX
    Explanations

    file path references in code

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

    include directives

    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
     propOrder
    -0.62
    AndEndTag
    -0.60
    +#+#
    -0.54
    webElementXpaths
    -0.53
    TintMode
    -0.52
     disambiguazione
    -0.49
    BITDA
    -0.48
    transQ
    -0.48
    clerview
    -0.48
    vaadin
    -0.47
    POSITIVE LOGITS
    CppMethod
    0.55
    脚注の使い方
    0.42
    BeginInit
    0.38
    Biografie
    0.36
     licenci
    0.36
    بوابة
    0.35
     descarga
    0.35
     Licence
    0.34
    Relevant
    0.34
    相关的
    0.34
    Activations Density 0.012%

    No Known Activations