Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6094
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and statutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    și
    -1.09
     theaters
    -1.08
     fibers
    -1.05
     tumors
    -1.00
     disks
    -0.97
    Theater
    -0.97
    Behaviors
    -0.97
     Theaters
    -0.96
     viață
    -0.95
     catalogs
    -0.95
    POSITIVE LOGITS
     Enquiries
    1.15
    ]',
    1.11
     licences
    1.10
     Colours
    1.08
     enquiries
    1.08
     artefacts
    1.05
     adverts
    1.05
     centralised
    1.04
     moulds
    1.03
     unauthorised
    1.02
    Activations Density 1.358%

    No Known Activations