© 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 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. 10942
    Prev
    Next
    INDEX
    Explanations

    references to newborns and associated sizes or recommendations

    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
    
    -0.46
    celess
    -0.44
    velocityY
    -0.42
    XmlIgnore
    -0.42
    љи
    -0.40
    块钱
    -0.40
     iš
    -0.40
    tudo
    -0.40
     ích
    -0.40
    zean
    -0.39
    POSITIVE LOGITS
    MemoryWarning
    0.90
     level
    0.84
     adult
    0.80
     smaller
    0.80
     scaled
    0.80
    EndContext
    0.79
     higher
    0.79
    Level
    0.79
     Adult
    0.78
     Level
    0.77
    Activations Density 0.770%

    No Known Activations