© 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. 18-GEMMASCOPE-RES-16K
    6. 8035
    Prev
    Next
    INDEX
    Explanations

    terms related to static electricity and its effects

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

    Electricity or electric-related terms

    np_acts-logits-general · gemini-2.0-flash

    electrical and static phenomena

    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
    ERVER
    -0.54
     Spicer
    -0.54
    visiae
    -0.53
    archer
    -0.53
     opium
    -0.53
     Satellite
    -0.51
    Тем
    -0.50
     Letras
    -0.50
     verloren
    -0.50
     السف
    -0.50
    POSITIVE LOGITS
     electric
    1.05
     ELECTRO
    1.04
     lightning
    1.01
     electro
    1.00
     Electro
    0.99
    electric
    0.94
     electrical
    0.94
     voltage
    0.93
     electricity
    0.93
    elect
    0.91
    Activations Density 0.440%

    No Known Activations