© 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. 24-GEMMASCOPE-RES-16K
    11. 4235
    Prev
    Next
    INDEX
    Explanations

    references to military or conflict-related actions

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

    Disruptions, shutdowns, and outages

    np_acts-logits-general · gemini-2.0-flash

    shutdowns, disruptions, power outages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RetentionPolicy
    -0.60
     tân
    -0.55
    atici
    -0.54
    ğraf
    -0.53
    ktive
    -0.52
     MainAxisSize
    -0.51
     divorced
    -0.51
    reshed
    -0.50
    ştir
    -0.49
    triangleq
    -0.49
    POSITIVE LOGITS
     disruption
    1.27
     disruptions
    1.21
     interruption
    1.11
     disrupted
    1.10
     disrupting
    1.06
     shutdown
    1.05
     interruptions
    1.03
     affected
    1.01
     outage
    1.00
     outages
    0.99
    Activations Density 0.204%

    No Known Activations