© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 80303
    Prev
    Next
    INDEX
    Explanations

    key historical references and significant timelines related to the United States

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

    reporting official website information

    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
    tagHelperRunner
    -0.40
    Imp
    -0.34
     اف
    -0.31
     pets
    -0.31
    افية
    -0.31
    SH
    -0.31
    发表于
    -0.31
     Imp
    -0.30
    Ich
    -0.30
    オリ
    -0.30
    POSITIVE LOGITS
    CloseOperation
    0.79
    SuspendLayout
    0.75
    PerformLayout
    0.72
    MLLoader
    0.71
    rungsseite
    0.70
    SequentialGroup
    0.68
     Paglinawan
    0.65
    SerializedSize
    0.64
    parsedMessage
    0.62
    CodedInputStream
    0.61
    Activations Density 0.094%

    No Known Activations