© 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. 15-GEMMASCOPE-RES-16K
    6. 2596
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to user interface actions and options in a web application context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.71
    ьаж
    -0.60
    новништво
    -0.57
    ftagPool
    -0.56
    NameInMap
    -0.55
     ProtoMessage
    -0.55
     '\\;'
    -0.54
    AddTagHelper
    -0.53
     &___
    -0.49
    ridge
    -0.48
    POSITIVE LOGITS
     يتيمه
    0.35
    ClientSize
    0.34
     创建时间
    0.31
    여
    0.29
     perpet
    0.29
     intptr
    0.29
    ICE
    0.29
    vaadin
    0.29
     作成
    0.29
    HomeAsUp
    0.28
    Activations Density 0.121%

    No Known Activations