© 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. 3-GEMMASCOPE-RES-16K
    11. 7197
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "Why do" or similar phrases that provoke thought or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -1.04
     تضيفلها
    -0.77
     AssemblyCulture
    -0.72
    XmlAccessorType
    -0.71
    CPtr
    -0.68
     Paglinawan
    -0.65
     propOrder
    -0.63
     referenties
    -0.63
    setVerticalGroup
    -0.61
     protoimpl
    -0.60
    POSITIVE LOGITS
     reason
    0.96
     why
    0.95
    reasons
    0.93
     reasons
    0.91
    why
    0.88
    reason
    0.88
    Reason
    0.85
     raisons
    0.85
     varför
    0.81
    Why
    0.81
    Activations Density 0.095%

    No Known Activations