© 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. 101599
    Prev
    Next
    INDEX
    Explanations

    sensory descriptions associated with various experiences

    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
     myſelf
    -0.62
     Verſ
    -0.59
     Inſ
    -0.56
     ſich
    -0.54
     ſie
    -0.53
     unicornio
    -0.53
     miniaturka
    -0.52
     ſind
    -0.52
     Geſ
    -0.51
    zbęd
    -0.50
    POSITIVE LOGITS
    rrggbb
    0.46
    richTextPanel
    0.37
     تضيفلها
    0.37
     nerves
    0.36
    +:+
    0.35
    ▀
    0.34
    toBeTruthy
    0.34
    expandindo
    0.34
     onPage
    0.34
     كورة
    0.33
    Activations Density 0.030%

    No Known Activations