© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 9219
    Prev
    Next
    INDEX
    Explanations

    elements and compounds related to chemical processes, particularly involving cells and electrochemistry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ArrayAdapter
    -0.57
     ilma
    -0.56
     NgModule
    -0.53
     chng
    -0.52
    ünstler
    -0.52
     TestBed
    -0.52
     fam
    -0.51
     fubject
    -0.50
    crição
    -0.50
     Wille
    -0.49
    POSITIVE LOGITS
     electrochemical
    0.87
     Electrochemical
    0.84
     electrode
    0.82
     Electrode
    0.80
     electrolysis
    0.76
     electrodes
    0.76
     voltam
    0.74
    electrode
    0.74
     Wiktionnaire
    0.69
     electrolytic
    0.65
    Activations Density 0.837%

    No Known Activations