© 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. 31-GEMMASCOPE-RES-16K
    11. 7727
    Prev
    Next
    INDEX
    Explanations

    data structures and collections in programming contexts

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

    generic type parameters with angle brackets in Java code (List<String>, Map<Integer, List<Integer>>, etc.).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createdBy
    -0.37
     packageName
    -0.35
     mAdapter
    -0.34
    DataSnapshot
    -0.32
    เกิน
    -0.30
     promoção
    -0.30
     goûts
    -0.29
     eventName
    -0.29
     isNameExpr
    -0.28
    tront
    -0.28
    POSITIVE LOGITS
    Personendaten
    0.68
     ब्रेकडाउन
    0.65
     kasarigan
    0.61
    ########.
    0.61
    
    0.57
    fjspx
    0.56
    tagPool
    0.55
    webElementXpaths
    0.55
     Normdatei
    0.52
     informée
    0.52
    Activations Density 0.054%

    No Known Activations