© 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. 7766
    Prev
    Next
    INDEX
    Explanations

    references to tables and comparisons of data within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Географиясе
    -0.58
    AsUp
    -0.47
    setViewName
    -0.47
     heapq
    -0.47
    mere
    -0.46
    xrLabel
    -0.43
    gherita
    -0.43
     ART
    -0.43
    SerializedSize
    -0.43
    UrlResolution
    -0.42
    POSITIVE LOGITS
     table
    0.70
     tables
    0.66
     AssemblyCulture
    0.60
     Table
    0.60
    Table
    0.59
     جدول
    0.58
     tabulated
    0.58
     tabel
    0.57
     tabela
    0.56
     tabla
    0.55
    Activations Density 0.834%

    No Known Activations