© 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-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 679
    Prev
    Next
    INDEX
    Explanations

    references to significant events, particularly earthquakes

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

    earthquake occurred, magnitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     &___
    -0.50
    tagHelperRunner
    -0.45
     الحره
    -0.42
     tartalomajánló
    -0.42
     mitään
    -0.42
     skills
    -0.41
    GTCX
    -0.38
    rungsseite
    -0.36
     disediakan
    -0.36
     øns
    -0.35
    POSITIVE LOGITS
     devastating
    0.66
     catastrophe
    0.62
     disaster
    0.62
     catastrophic
    0.60
     disastrous
    0.59
     devastation
    0.57
     devast
    0.56
     katastro
    0.55
     magnitud
    0.55
    Disaster
    0.55
    Activations Density 0.022%

    No Known Activations