© 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. 13548
    Prev
    Next
    INDEX
    Explanations

    nouns related to specific locations, events, and organizational structures

    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
    ibatis
    -0.44
     siguran
    -0.44
     uș
    -0.43
     PyQt
    -0.43
    clash
    -0.42
     حض
    -0.40
    roidery
    -0.40
    DebuggerStep
    -0.40
    #:
    -0.40
    /$',
    -0.39
    POSITIVE LOGITS
    Datuak
    0.73
     disambiguazione
    0.67
    قایناقلار
    0.64
    ंदीखरीदारी
    0.64
    Vidite
    0.63
     distanciation
    0.63
    addCriterion
    0.62
     विश्वसनीयता
    0.62
    istocene
    0.60
     &___
    0.59
    Activations Density 0.647%

    No Known Activations