© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15436
    Prev
    Next
    INDEX
    Explanations

    numerical references and figures related to research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Citations referring to figures

    np_acts-logits-general · gemini-2.0-flash

    legal citations and figure references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Urdu
    -0.49
    SBATCH
    -0.48
     Canad
    -0.46
    cfm
    -0.46
     Sched
    -0.45
    cae
    -0.45
     Byrd
    -0.45
    Partager
    -0.44
     essenti
    -0.44
     Turch
    -0.44
    POSITIVE LOGITS
    webElementXpaths
    0.69
    richTextPanel
    0.67
     ***!
    0.66
     Wellesley
    0.64
    signable
    0.64
    
    0.63
     Massachusetts
    0.62
     useAppContext
    0.62
     समीक्षाएं
    0.61
     Catalana
    0.61
    Activations Density 0.410%

    No Known Activations