© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 1367
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significance or notable effects in research data

    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
    bra
    -0.66
    AspNetCore
    -0.65
    ReusableCell
    -0.64
     try
    -0.63
     Thron
    -0.63
    ো
    -0.63
    klo
    -0.62
    dro
    -0.62
    op
    -0.61
     encarga
    -0.61
    POSITIVE LOGITS
    ificantly
    1.47
    ificance
    1.46
    ificant
    1.44
    BibitemShut
    1.30
     SIGNIFIC
    1.18
     significant
    1.18
     myſelf
    1.14
    ']))
    
    1.14
    Significant
    1.14
    ")));
    
    1.11
    Activations Density 0.145%

    No Known Activations