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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 15589
    Prev
    Next
    INDEX
    Explanations

    references to specific events or details regarding significant disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     annually
    -0.42
     AssemblyCulture
    -0.42
    RetentionPolicy
    -0.41
    غيرة
    -0.41
     anuales
    -0.40
     pério
    -0.40
     anual
    -0.40
     annual
    -0.39
     jährlich
    -0.39
     Annual
    -0.39
    POSITIVE LOGITS
     evacu
    1.09
     evac
    1.08
     evacuation
    1.07
     evacuated
    1.07
     evacuate
    1.05
     survivors
    0.99
     rescu
    0.89
     rescue
    0.87
     casualties
    0.83
    救援
    0.81
    Activations Density 0.272%

    No Known Activations