© 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. 25-GEMMASCOPE-RES-16K
    11. 477
    Prev
    Next
    INDEX
    Explanations

    terms related to publishing and copyright law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to copyright, legal rights, and historical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    queryInterface
    -0.67
     насеље
    -0.60
    ThroughAttribute
    -0.58
     OFDb
    -0.57
     @"/
    -0.51
     AspNetCore
    -0.51
     lenker
    -0.50
     AssemblyTitle
    -0.49
     emot
    -0.49
    RTLI
    -0.48
    POSITIVE LOGITS
     reprint
    1.05
     printing
    1.04
     publication
    1.04
     republished
    1.03
     published
    1.02
     reprinted
    1.02
     reprints
    1.00
     editions
    0.99
     printed
    0.97
     publish
    0.96
    Activations Density 0.464%

    No Known Activations