© 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
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9841
    Prev
    Next
    INDEX
    Explanations

    tokens representing the start of segments or blocks in structured text, such as code or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     berwarna
    -0.31
    CloseOperation
    -0.29
    لينكات
    -0.28
     points
    -0.28
     signing
    -0.28
    spirited
    -0.27
     toujours
    -0.27
    c
    -0.27
    되어
    -0.27
     picking
    -0.26
    POSITIVE LOGITS
    ⓧ
    0.82
    Autoritní
    0.77
     AssemblyCompany
    0.74
    setVerticalGroup
    0.69
    تقاوى
    0.67
     Мексичка
    0.65
    Aholisi
    0.63
     queſta
    0.62
    windowFixed
    0.61
    SourceChecksum
    0.61
    Activations Density 1.642%

    No Known Activations