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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 10505
    Prev
    Next
    INDEX
    Explanations

    references to attendance at meetings or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']))
    
    -0.78
    ]))
    
    -0.74
    '))
    
    -0.71
    ("");
    
    -0.70
    ')))
    -0.67
     Ras
    -0.66
    (""))
    -0.65
    ]));
    
    -0.61
    ]:
    
    -0.61
    '])
    
    -0.60
    POSITIVE LOGITS
     attend
    2.44
     Attend
    2.33
     attended
    2.32
     Attending
    2.30
     attends
    2.30
     attending
    2.27
     attendance
    2.19
    Attend
    2.09
    attend
    2.08
     ATTEND
    2.07
    Activations Density 0.154%

    No Known Activations