© 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. 30-GEMMASCOPE-RES-16K
    11. 11529
    Prev
    Next
    INDEX
    Explanations

    elements related to code structure and functionality

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

    preceding "controller" or related terms

    np_acts-logits-general · gemini-2.0-flash

    controller files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.41
    oneofs
    -0.35
     participação
    -0.35
     capaz
    -0.34
    prelude
    -0.34
     cenar
    -0.34
    tidaknya
    -0.34
     capacidad
    -0.33
     apuestas
    -0.33
     almohada
    -0.32
    POSITIVE LOGITS
     controller
    1.55
     Controller
    1.52
     controllers
    1.45
     Controllers
    1.41
    Controller
    1.33
    controller
    1.32
    controllers
    1.17
    控制器
    1.16
    Controllers
    1.13
    CONTROLLER
    1.06
    Activations Density 0.699%

    No Known Activations