© 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. 15-GEMMASCOPE-RES-16K
    11. 736
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical sampling and sparsity concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
     myſelf
    -0.88
     itſelf
    -0.87
     raiſ
    -0.79
     anſ
    -0.72
     ſtand
    -0.71
     uſed
    -0.70
     ſta
    -0.70
     himſelf
    -0.69
     leſs
    -0.69
     purpoſe
    -0.67
    POSITIVE LOGITS
     Infórmanos
    0.46
    detectChanges
    0.42
    lioz
    0.42
    routeProvider
    0.41
    fillStyle
    0.40
    новниш
    0.40
     montagem
    0.40
    nasium
    0.40
    힣
    0.40
     ^=
    0.40
    Activations Density 1.905%

    No Known Activations