© 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. 31-GEMMASCOPE-RES-16K
    11. 4638
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize supportive and empowering interactions within relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    emotional or significant moments where people express personal values, desires, and life choices.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    исленность
    -0.54
    featureID
    -0.49
    GenerationType
    -0.48
    cstring
    -0.48
    XmlAccessorType
    -0.48
    findOrFail
    -0.47
    IBarButtonItem
    -0.46
    leneck
    -0.45
    DIPSETTING
    -0.45
    webElementXpaths
    -0.45
    POSITIVE LOGITS
     they
    3.09
     mereka
    2.80
     loro
    2.75
     their
    2.72
    Their
    2.67
    他們
    2.64
    They
    2.52
    their
    2.52
    他们
    2.45
     Their
    2.45
    Activations Density 3.875%

    No Known Activations