© 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. 2-GEMMASCOPE-RES-16K
    11. 1959
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rush" and its variations, indicating urgency or haste

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.75
     الحره
    -0.73
    OCCURRED
    -0.68
    setHorizontal
    -0.68
     gynhyrchwyd
    -0.67
    лару
    -0.66
     Audiodateien
    -0.64
     protoimpl
    -0.64
     NgModule
    -0.63
    بوابة
    -0.60
    POSITIVE LOGITS
     rush
    1.35
     urge
    1.08
     RUSH
    1.04
    Rush
    1.02
     Rush
    1.01
     rushed
    0.94
    rush
    0.93
     rushes
    0.85
     crowd
    0.84
     hurry
    0.83
    Activations Density 0.058%

    No Known Activations