© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 5932
    Prev
    Next
    INDEX
    Explanations

    discussions about transparency and honesty in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ledes
    -0.57
     Magee
    -0.53
    menschen
    -0.49
    autorelease
    -0.48
     Vella
    -0.48
     pisang
    -0.47
    rdı
    -0.46
     jurí
    -0.45
     Purdy
    -0.45
    vscode
    -0.45
    POSITIVE LOGITS
     disclosing
    0.89
     revealing
    0.87
     disclosure
    0.86
     disclose
    0.83
     transparency
    0.82
     disclosures
    0.79
     discloses
    0.78
     honesty
    0.77
     frank
    0.76
     openly
    0.76
    Activations Density 0.228%

    No Known Activations