© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101324
    Prev
    Next
    INDEX
    Explanations

    themes centered around social justice and poverty alleviation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    getDoctrine
    -0.54
    qtype
    -0.45
    Enllaces
    -0.45
     cre
    -0.43
     חיצוניים
    -0.43
    arXiv
    -0.42
     nhật
    -0.40
     poch
    -0.40
    AFX
    -0.40
    참고
    -0.39
    POSITIVE LOGITS
     pinulongan
    0.45
     famine
    0.45
     ISTAT
    0.44
    şört
    0.44
     Infórmanos
    0.41
     measles
    0.40
     pouvoit
    0.39
     FetchType
    0.38
    ปัญ
    0.37
    Портали
    0.37
    Activations Density 0.027%

    No Known Activations