© 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. 9-GEMMASCOPE-RES-16K
    6. 1986
    Prev
    Next
    INDEX
    Explanations

    references to infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yarmouth
    -0.99
     Hoyt
    -0.97
     Geologist
    -0.95
     judiciaire
    -0.95
    endphp
    -0.94
     Oldham
    -0.88
     Saito
    -0.88
     Vian
    -0.87
     Amad
    -0.85
    UnknownFieldSet
    -0.84
    POSITIVE LOGITS
     infrastructure
    1.75
     infrastructures
    1.61
     infra
    1.48
     Infrastructure
    1.47
    infrastructure
    1.32
     Infra
    1.29
    Infra
    1.23
    Infrastructure
    1.23
    infra
    1.19
    frastructure
    1.12
    Activations Density 0.051%

    No Known Activations