© 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. 12-GEMMASCOPE-RES-16K
    11. 5438
    Prev
    Next
    INDEX
    Explanations

    scroll-related attributes and properties in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tri
    -0.40
     Shape
    -0.40
     zy
    -0.39
     Syner
    -0.39
     Stu
    -0.39
     Zy
    -0.39
     shape
    -0.38
     seed
    -0.37
    Shape
    -0.37
     Fel
    -0.37
    POSITIVE LOGITS
    ChildScrollView
    1.52
    crollView
    1.43
    Scroll
    1.27
    scroll
    1.26
     scroll
    1.25
     Scroll
    1.19
    croll
    1.15
     scrolls
    1.11
    ScrollView
    1.09
     scrolling
    1.05
    Activations Density 0.204%

    No Known Activations