© 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. 18-GEMMASCOPE-RES-16K
    11. 11218
    Prev
    Next
    INDEX
    Explanations

    instances of crowd behavior and the challenges faced in lines or queuing situations

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

    waiting in lines or queues

    np_acts-logits-general · gemini-2.0-flash

    standing in line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ätigkeit
    -0.47
    ьаж
    -0.47
    tran
    -0.47
    loose
    -0.47
    rief
    -0.44
    bruch
    -0.43
    szer
    -0.43
    Dữ
    -0.42
    confidence
    -0.42
     συνε
    -0.42
    POSITIVE LOGITS
     queue
    1.81
     queuing
    1.74
     queues
    1.71
     waiting
    1.50
     Queue
    1.46
     queued
    1.39
     wait
    1.38
     Waiting
    1.33
    queue
    1.32
     waits
    1.30
    Activations Density 0.100%

    No Known Activations