© 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. 17-GEMMASCOPE-RES-16K
    6. 4504
    Prev
    Next
    INDEX
    Explanations

    references to biological data analysis and computational techniques in scientific literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idéia
    -0.77
     convenable
    -0.64
     daß
    -0.64
     biß
    -0.63
     Einfluß
    -0.62
     Bewußt
    -0.58
     muß
    -0.58
    faßt
    -0.58
     chré
    -0.57
     merveille
    -0.57
    POSITIVE LOGITS
    NameInMap
    0.91
     microbiome
    0.88
     onboarding
    0.87
     disambiguazione
    0.86
     incentiv
    0.83
    jsii
    0.79
     impactful
    0.79
    lably
    0.78
     leveraging
    0.78
     estekak
    0.78
    Activations Density 4.439%

    No Known Activations