© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 13616
    Prev
    Next
    INDEX
    Explanations

    references to natural human behavior or tendencies

    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
    Autoritní
    -0.57
     utafitiHapana
    -0.57
    :✨
    -0.55
    rungsseite
    -0.53
    <bos>
    -0.52
    katu
    -0.50
    SourceChecksum
    -0.50
    Kanpo
    -0.48
    asana
    -0.48
    Termine
    -0.48
    POSITIVE LOGITS
     naturally
    0.96
     inevitably
    0.95
     instinctively
    0.89
    Naturally
    0.84
     inevitable
    0.83
     Naturally
    0.78
     instinct
    0.74
    inev
    0.72
     naturalmente
    0.72
     natürlich
    0.71
    Activations Density 0.253%

    No Known Activations