© 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. 12-GEMMASCOPE-RES-16K
    6. 10464
    Prev
    Next
    INDEX
    Explanations

    mentions of inevitability and the natural progression of life events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dees
    -0.53
    AYA
    -0.52
    gai
    -0.52
    quois
    -0.51
     qualified
    -0.51
    inaldi
    -0.51
    ]!='
    -0.50
     poi
    -0.50
    INDER
    -0.50
    gonic
    -0.50
    POSITIVE LOGITS
     normaux
    0.77
     réguli
    0.76
     énergé
    0.67
    expandindo
    0.65
     définiti
    0.63
     culturelles
    0.63
     noires
    0.62
     normais
    0.62
     engraçadas
    0.61
     traditionnels
    0.60
    Activations Density 0.327%

    No Known Activations