© 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. 10-GEMMASCOPE-RES-16K
    11. 8721
    Prev
    Next
    INDEX
    Explanations

    unusual or non-standard characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.54
    -
    -0.52
    ,
    -0.51
     &
    -0.51
     O
    -0.51
    ata
    -0.49
     is
    -0.48
    5
    -0.46
    O
    -0.46
     
    -0.46
    POSITIVE LOGITS
     فريبيس
    1.36
    MigrationBuilder
    1.22
    LookAnd
    1.16
     AssemblyCulture
    1.06
    脚注の使い方
    1.04
     مرئيه
    1.03
     Савезне
    1.02
    Hochspringen
    1.01
     Мексичка
    1.01
    ंदीखरीदारी
    1.00
    Activations Density 0.477%

    No Known Activations