© 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. 22-GEMMASCOPE-RES-16K
    11. 16346
    Prev
    Next
    INDEX
    Explanations

    references to safety and warning systems, particularly in the context of transportation and emergency alerts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    warnings or alerts

    np_acts-logits-general · gemini-2.0-flash

    detecting and warning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.59
    FormTagHelper
    -0.53
    WireFormatLite
    -0.53
    ItemLayout
    -0.51
    زینه
    -0.51
    Spons
    -0.50
     الحره
    -0.48
     fossils
    -0.48
     Familienname
    -0.47
    GetEnumerator
    -0.47
    POSITIVE LOGITS
     warning
    2.48
     alert
    2.36
     alerts
    2.24
     warnings
    2.19
     Alert
    2.13
     warn
    2.11
     Warning
    2.10
     alerting
    2.10
     alarm
    1.98
    alert
    1.98
    Activations Density 0.415%

    No Known Activations