© 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. 8-GEMMASCOPE-RES-16K
    11. 10812
    Prev
    Next
    INDEX
    Explanations

    terms related to biochemical compounds and protein structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.81
    ddha
    -0.74
    moveToFirst
    -0.72
    voorbeeld
    -0.68
    ntgen
    -0.67
     mdl
    -0.64
    mender
    -0.64
    NAND
    -0.63
    ‚¬
    -0.62
     فريبيس
    -0.62
    POSITIVE LOGITS
    pable
    1.15
     FAP
    1.09
     Jop
    1.08
    Jep
    1.07
     bop
    1.03
     cip
    1.02
     Bop
    1.02
     Wap
    1.00
     Jep
    1.00
     Zapata
    0.98
    Activations Density 2.057%

    No Known Activations