© 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. 11-GEMMASCOPE-RES-16K
    11. 11310
    Prev
    Next
    INDEX
    Explanations

    phrases related to transformation or conversion of concepts and elements into something new or improved

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abstractmethod
    -0.65
    PerformLayout
    -0.59
    SequentialGroup
    -0.59
    WriteBarrier
    -0.57
     ویکی‌پدی
    -0.57
    AddTagHelper
    -0.54
    Diwedd
    -0.54
     Überblick
    -0.52
     الاطلاع
    -0.52
    IBOutlet
    -0.52
    POSITIVE LOGITS
     transformed
    0.77
     превра
    0.73
     transforming
    0.69
     transforms
    0.67
     تبدیل
    0.65
     trasform
    0.64
     converted
    0.64
     Transforming
    0.63
     converts
    0.62
     transformation
    0.59
    Activations Density 0.533%

    No Known Activations