© 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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 9045
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and hypothesis testing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.52
    webElementGuid
    -0.52
    queryInterface
    -0.51
    
    -0.51
    ழ்
    -0.51
    UpInside
    -0.51
     BoxFit
    -0.49
    InitVars
    -0.48
     Beale
    -0.48
    migrationBuilder
    -0.47
    POSITIVE LOGITS
    ArrowToggle
    0.68
    лару
    0.61
     gainera
    0.59
    MemoryWarning
    0.59
     isInitialized
    0.58
    rektur
    0.58
     himo
    0.57
    зулта
    0.56
    τως
    0.56
    featureID
    0.56
    Activations Density 0.703%

    No Known Activations