© 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 - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9627
    Prev
    Next
    INDEX
    Explanations

    references to parliamentary governance and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    archiviato
    -0.71
    SequentialGroup
    -0.70
     HasFactory
    -0.69
    ValueStyle
    -0.68
    randomUUID
    -0.66
    发表于
    -0.63
    conio
    -0.63
    iettes
    -0.62
     تضيفلها
    -0.62
    InSection
    -0.59
    POSITIVE LOGITS
     Stir
    0.88
    Stir
    0.84
     stir
    0.77
     parliament
    0.77
    stir
    0.76
     Parliament
    0.75
     stirring
    0.75
     stirred
    0.71
     سكانية
    0.69
    ところで
    0.66
    Activations Density 0.084%

    No Known Activations