© 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. 5-GEMMASCOPE-RES-16K
    6. 13579
    Prev
    Next
    INDEX
    Explanations

    confirmation statements and assertions in a programming context, especially related to testing and validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.75
     betweenstory
    -0.73
     externi
    -0.71
    Jeografia
    -0.67
    Notae
    -0.63
     nakalista
    -0.62
    ……"
    -0.61
    labus
    -0.61
     fieldNum
    -0.61
    Vidite
    -0.59
    POSITIVE LOGITS
    slidesPer
    0.55
    erobic
    0.54
    queryInterface
    0.51
     
    0.51
    yelitis
    0.51
    usermodel
    0.51
    WidgetItem
    0.50
    TableHead
    0.48
    logii
    0.48
    beforeSend
    0.48
    Activations Density 0.022%

    No Known Activations