© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 15856
    Prev
    Next
    INDEX
    Explanations

    concepts related to machine learning, specifically focusing on gradient-based methods and parameters in CNNs

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

    Gradients and backpropagation in neural networks

    np_acts-logits-general · gemini-2.0-flash

    backpropagation signal and gradient maps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Assay
    -0.55
    rungsseite
    -0.55
     handlebar
    -0.54
     fullscreen
    -0.51
    //
    -0.51
     Breed
    -0.50
     Dispens
    -0.50
     concurs
    -0.50
    arker
    -0.49
     Италијани
    -0.49
    POSITIVE LOGITS
     learning
    0.79
     momentum
    0.73
     update
    0.71
     gradient
    0.69
     Momentum
    0.68
     updates
    0.67
     SGD
    0.65
     Update
    0.65
     grad
    0.64
     updating
    0.64
    Activations Density 0.346%

    No Known Activations