© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1000
    Prev
    Next
    INDEX
    Explanations

    formatting markers or headers typically used in structured documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     […]
    -0.54
    ่านั้น
    -0.53
    ิ้ง
    -0.47
    }%
    -0.44
     ...
    -0.43
    𝗿
    -0.42
     alberto
    -0.39
     nahilalakip
    -0.39
     [...]
    -0.39
    ๋า
    -0.39
    POSITIVE LOGITS
    Personensuche
    1.31
    kloped
    1.09
     CreateTagHelper
    1.06
     typelib
    1.03
     autorytatywna
    1.01
    SequentialGroup
    0.97
    клопе
    0.94
     Савезне
    0.94
     تضيفلها
    0.93
     defaultstate
    0.92
    Activations Density 0.003%

    No Known Activations