© 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. 22-GEMMASCOPE-RES-16K
    11. 6036
    Prev
    Next
    INDEX
    Explanations

    references to various newspapers and their publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lightboxes
    -0.48
     Udemy
    -0.46
    AddTagHelper
    -0.44
     invokingState
    -0.44
     Kön
    -0.42
     <>",
    -0.42
    исленность
    -0.42
    UTELY
    -0.41
    localctx
    -0.41
     Vimeo
    -0.40
    POSITIVE LOGITS
     newspaper
    1.09
     Newspaper
    1.00
     newspapers
    0.99
     Newspapers
    0.92
    Newspaper
    0.88
    newspaper
    0.85
    报纸
    0.74
     journaux
    0.68
     periódico
    0.66
     газе
    0.65
    Activations Density 0.176%

    No Known Activations