© 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. 10-GEMMASCOPE-RES-16K
    6. 8089
    Prev
    Next
    INDEX
    Explanations

    references to indices or data structures in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getCustomer
    -0.48
    UserScript
    -0.44
     Tremb
    -0.44
     Girolamo
    -0.43
     Continu
    -0.41
     getApplication
    -0.41
     gdyby
    -0.41
    COMPLETED
    -0.41
    toHaveBeenCalled
    -0.41
     
    -0.40
    POSITIVE LOGITS
     index
    2.27
     Index
    2.20
    Index
    2.06
    index
    2.02
     INDEX
    1.90
    INDEX
    1.76
     indexes
    1.67
    getIndex
    1.59
     Indexes
    1.54
     indices
    1.53
    Activations Density 0.241%

    No Known Activations