© 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. 15-GEMMASCOPE-RES-16K
    11. 6096
    Prev
    Next
    INDEX
    Explanations

    references to the most recent information or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imageshack
    -0.75
    CDF
    -0.68
     Raccoon
    -0.66
    Kalb
    -0.65
     goa
    -0.64
    AnchorStyles
    -0.62
    endous
    -0.61
    ="@+
    -0.61
    Recognizer
    -0.60
    Shrek
    -0.60
    POSITIVE LOGITS
    LATEST
    1.01
     latest
    1.01
    latest
    0.97
     LATEST
    0.96
    Latest
    0.93
     Latest
    0.89
    最新的
    0.84
     updates
    0.84
     最新
    0.82
    最新の
    0.80
    Activations Density 0.056%

    No Known Activations