© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13350
    Prev
    Next
    INDEX
    Explanations

    concepts related to energy conversion and thermodynamic processes

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

    energy and heat exchange

    np_acts-logits-general · gemini-2.0-flash

    energy and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    万人
    -0.60
    IUrlHelper
    -0.58
     titration
    -0.54
     hemma
    -0.50
     Woodruff
    -0.50
     tetrachloride
    -0.48
     дож
    -0.47
     Thickness
    -0.47
    õi
    -0.47
     polyg
    -0.47
    POSITIVE LOGITS
     energy
    1.44
    energy
    1.25
     Energy
    1.17
    Energy
    1.16
     ENERGY
    1.07
    ENERGY
    0.97
     energia
    0.97
    énergie
    0.96
     kinetic
    0.94
     energies
    0.92
    Activations Density 0.402%

    No Known Activations