© 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. 2-GEMMASCOPE-RES-16K
    6. 3796
    Prev
    Next
    INDEX
    Explanations

    references to object types and structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.67
     betweenstory
    -0.55
     يتيمه
    -0.55
     malheur
    -0.54
     Photocase
    -0.53
    LookAnd
    -0.52
    onViewCreated
    -0.52
     meisje
    -0.52
     ProtoMessage
    -0.49
    rician
    -0.49
    POSITIVE LOGITS
     ↑
    0.62
    Object
    0.58
     Daily
    0.52
     Classic
    0.52
     classic
    0.50
     Object
    0.50
    Classic
    0.50
    Daily
    0.49
     DAILY
    0.47
    DAILY
    0.47
    Activations Density 0.077%

    No Known Activations