© 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. 11-GEMMASCOPE-RES-16K
    11. 4372
    Prev
    Next
    INDEX
    Explanations

    references to significant events or statements related to community gatherings or urgent discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XtraGrid
    -0.29
     habet
    -0.29
     dedans
    -0.29
    :✨
    -0.29
     totul
    -0.28
    @[+][
    -0.28
    InStock
    -0.28
     AssemblyCulture
    -0.27
     вжи
    -0.27
     noyau
    -0.26
    POSITIVE LOGITS
    uxxxx
    0.77
     Италијани
    0.66
    CppMethod
    0.65
     controversial
    0.57
     ujednoznacz
    0.57
     nahilalakip
    0.56
    Personendaten
    0.55
    Appellants
    0.55
     intptr
    0.55
     مواليد
    0.55
    Activations Density 1.029%

    No Known Activations