Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2815
    Prev
    Next
    INDEX
    Explanations

    themes related to truth, reality, and personal authenticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InSection
    -0.56
     Reuter
    -0.55
     pria
    -0.50
     industriels
    -0.49
     adaptés
    -0.48
    elé
    -0.47
    出版年
    -0.47
     entradas
    -0.47
    ographique
    -0.47
    록
    -0.47
    POSITIVE LOGITS
     reveals
    0.79
     Exposed
    0.78
     exposed
    0.77
     revealing
    0.74
     revealed
    0.74
    Exposed
    0.73
     fragility
    0.73
     reveal
    0.70
     exposes
    0.67
    exposed
    0.66
    Activations Density 0.183%

    No Known Activations