© 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. 20-GEMMASCOPE-RES-16K
    11. 15924
    Prev
    Next
    INDEX
    Explanations

    themes related to loyalty and responsibility in relationships or societal roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.43
    ViewImports
    -0.43
    PerformLayout
    -0.42
    itinéraire
    -0.40
    tagHelperRunner
    -0.36
    싶
    -0.35
    getOutputStream
    -0.35
    しまいました
    -0.34
    quitous
    -0.32
    舺
    -0.32
    POSITIVE LOGITS
    хіво
    0.54
     ujednoznacz
    0.54
    Also
    0.52
     pula
    0.51
    __]
    0.50
     also
    0.47
     becauſe
    0.47
     myös
    0.46
     anche
    0.45
     cả
    0.44
    Activations Density 0.372%

    No Known Activations