Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10333
    Prev
    Next
    INDEX
    Explanations

    instances of the word "attend" and its variations, indicating a focus on attendance or participation in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']))
    
    -0.75
    基
    -0.67
    ]))
    
    -0.65
     Ras
    -0.65
     $
    -0.64
    '))
    
    -0.62
    ("");
    
    -0.61
    ak
    -0.60
    Substances
    -0.59
    ras
    -0.58
    POSITIVE LOGITS
     attend
    2.67
     attended
    2.55
     attends
    2.52
     Attend
    2.50
     Attending
    2.48
     attending
    2.47
     attendance
    2.29
    Attend
    2.26
    attend
    2.24
     ATTEND
    2.20
    Activations Density 0.141%

    No Known Activations