© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 3128
    Prev
    Next
    INDEX
    Explanations

    text related to aviation and aircraft configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    diocese
    -0.51
     kayaking
    -0.50
     Invisalign
    -0.48
    rouvez
    -0.47
    esModule
    -0.46
     Magnetism
    -0.45
     humana
    -0.45
     CarPlay
    -0.44
     Borel
    -0.44
    ctose
    -0.44
    POSITIVE LOGITS
     machine
    1.15
     beast
    1.01
     machines
    1.00
     device
    0.97
     macchina
    0.96
     vehicle
    0.94
    machine
    0.92
     máquina
    0.90
     apparaat
    0.88
    appareil
    0.87
    Activations Density 0.584%

    No Known Activations