© 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. 37-GEMMASCOPE-RES-16K
    11. 6504
    Prev
    Next
    INDEX
    Explanations

    references to the Internet of Things (IoT) and related technological concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Trayectoria
    -0.38
    Географиясе
    -0.35
     Ums
    -0.35
    PLANATION
    -0.32
    beitung
    -0.32
     Ausgleich
    -0.32
     Emig
    -0.31
    исленность
    -0.31
     copas
    -0.30
    Préparation
    -0.30
    POSITIVE LOGITS
     IoT
    1.45
     smart
    1.27
    IoT
    1.25
     sensors
    1.11
     Smart
    1.09
     IOT
    1.06
    smart
    1.05
     sensor
    1.05
    Smart
    0.97
    iot
    0.94
    Activations Density 0.449%

    No Known Activations