© 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. 5462
    Prev
    Next
    INDEX
    Explanations

    terms related to programming or markup language elements and mathematical rules or structures

    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
    <eos>
    -0.51
     Cap
    -0.50
    /-
    -0.46
    /.
    -0.45
    erals
    -0.44
    ,
    -0.44
    .
    -0.44
    पर
    -0.44
     Sim
    -0.43
     Walters
    -0.43
    POSITIVE LOGITS
    multicolumn
    4.30
    multirow
    2.07
    存于互联网档案馆
    1.31
    \{\\
    1.28
    enumi
    1.20
     שוליים
    1.17
    ConstraintMaker
    1.16
    BeginContext
    1.16
     nahilalakip
    1.13
    IsContent
    1.12
    Activations Density 0.008%

    No Known Activations