© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4747
    Prev
    Next
    INDEX
    Explanations

    imports related to programming libraries, particularly for Android and Java

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

    Java/C++ import statements

    np_acts-logits-general · gemini-2.0-flash

    programming language imports

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Verme
    -0.31
     Ä
    -0.30
     получается
    -0.30
    <eos>
    -0.30
    ie
    -0.29
     style
    -0.29
    ty
    -0.29
     and
    -0.28
    хіво
    -0.28
    ta
    -0.28
    POSITIVE LOGITS
     للمعارف
    0.94
     initComponents
    0.89
     propOrder
    0.88
     الحره
    0.85
     CreateTagHelper
    0.75
    BeginInit
    0.73
     للاسماء
    0.71
    XmlAccessorType
    0.70
    [@BOS@]
    0.69
    <unused3>
    0.69
    Activations Density 0.028%

    No Known Activations