© 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. 10267
    Prev
    Next
    INDEX
    Explanations

    references to formal structures, classifications, and criteria in various domains

    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
     Butterfield
    -0.76
    łgorzata
    -0.72
     ویکی‌آمباردا
    -0.71
     Paulus
    -0.70
    IUrlHelper
    -0.70
     Colette
    -0.68
    shub
    -0.68
     Erfurt
    -0.67
     ModelExpression
    -0.67
     الحره
    -0.67
    POSITIVE LOGITS
    ran
    1.08
    aran
    1.01
    lan
    1.00
    han
    1.00
    ban
    1.00
    nnnn
    0.99
    ajan
    0.98
    ikan
    0.97
    nan
    0.96
     Cranston
    0.96
    Activations Density 3.183%

    No Known Activations