© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 14007
    Prev
    Next
    INDEX
    Explanations

    elements related to gradients and their manipulation in experiments or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.59
     protoimpl
    -0.50
    protoimpl
    -0.44
    ſelf
    -0.44
    MarshalTo
    -0.43
    setColumns
    -0.42
     ActionResult
    -0.42
    OCCURRED
    -0.40
     houſe
    -0.40
     IActionResult
    -0.39
    POSITIVE LOGITS
     gradient
    0.81
     gradients
    0.74
     Gradient
    0.71
    gradient
    0.70
    Gradient
    0.69
     GRAD
    0.57
    渐变
    0.54
    dients
    0.53
     grad
    0.52
     gradi
    0.49
    Activations Density 1.126%

    No Known Activations