© 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. 1-GEMMASCOPE-RES-16K
    11. 10217
    Prev
    Next
    INDEX
    Explanations

    terms related to extraction processes and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ApplicationTests
    -0.62
    phism
    -0.60
    WarningLevel
    -0.60
    stateParams
    -0.55
    cheibe
    -0.54
    ומית
    -0.53
    Cubit
    -0.52
    ступление
    -0.52
    }?
    -0.51
     nueces
    -0.51
    POSITIVE LOGITS
     extraction
    1.25
    TC
    1.17
     Extraction
    1.17
    extraction
    1.05
    Extraction
    1.05
     TC
    1.00
     extract
    1.00
     extracting
    0.95
    extract
    0.89
    extracted
    0.87
    Activations Density 0.082%

    No Known Activations