© 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. 22-GEMMASCOPE-RES-16K
    11. 5606
    Prev
    Next
    INDEX
    Explanations

    semantic structures related to data types and function definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Khe
    -0.44
    zelt
    -0.43
    ſſed
    -0.42
    ㅐ
    -0.41
    lassified
    -0.40
    erialization
    -0.39
    MENAFN
    -0.39
     ProtoMessage
    -0.38
    笹
    -0.38
     Imper
    -0.38
    POSITIVE LOGITS
    addGroup
    0.48
    Revenir
    0.47
    richTextPanel
    0.45
    parsedMessage
    0.43
    AsUp
    0.42
     HttpNotFound
    0.42
     intStringLen
    0.42
     nahilalakip
    0.39
    MessageState
    0.38
    InSection
    0.37
    Activations Density 1.503%

    No Known Activations