© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6831
    Prev
    Next
    INDEX
    Explanations

    performance statistics related to sports and awards

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

    sports statistics and numerical performance metrics, particularly in basketball.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    CppMethod
    -0.63
    EndInit
    -0.60
    BeginInit
    -0.59
    GTCX
    -0.58
     հղումներ
    -0.57
    ibal
    -0.56
     invokingState
    -0.55
     pinulongan
    -0.55
    __(/*!
    -0.54
    RefNanny
    -0.54
    POSITIVE LOGITS
     AssemblyTitle
    0.50
     Fernsehen
    0.39
     actionPerformed
    0.38
     mouseClicked
    0.37
    ClCompile
    0.37
    новниш
    0.35
     Američ
    0.35
     allgemeinen
    0.34
    føl
    0.33
    accompag
    0.33
    Activations Density 0.814%

    No Known Activations