© 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. 10-GEMMASCOPE-RES-16K
    6. 8418
    Prev
    Next
    INDEX
    Explanations

    programming constructs and code-related syntax, particularly in the context of React components and API interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -1.02
     InputDecoration
    -0.92
    ArrowToggle
    -0.78
    __*/
    -0.75
    AnimationsModule
    -0.75
    IBOutlet
    -0.75
    \{\\
    -0.74
    onViewCreated
    -0.73
    UrlResolution
    -0.73
     resourceCulture
    -0.72
    POSITIVE LOGITS
     perut
    0.34
     vzor
    0.33
     divisão
    0.32
     väč
    0.32
     živ
    0.32
     potrzeb
    0.31
     kjem
    0.31
     économies
    0.31
    lowercase
    0.31
     potřeb
    0.30
    Activations Density 0.199%

    No Known Activations