© 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 - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 7955
    Prev
    Next
    INDEX
    Explanations

    references to historical or familial backgrounds and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.69
     today
    -0.50
    today
    -0.50
    ectors
    -0.49
    complexContent
    -0.48
    今夜
    -0.48
     okuyayım
    -0.48
    endio
    -0.47
    stdc
    -0.47
    Хьажоргаш
    -0.46
    POSITIVE LOGITS
     habían
    1.20
     had
    1.12
     sebelumnya
    1.11
     zuvor
    1.11
     había
    1.10
     havia
    1.07
     hadn
    1.05
     earlier
    1.02
     wcześniej
    0.98
     previously
    0.96
    Activations Density 0.646%

    No Known Activations