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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 9291
    Prev
    Next
    INDEX
    Explanations

    references to bathrooms and sanitation facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.57
     صوتيه
    -0.55
    __.__
    -0.54
    })));
    -0.53
    brokers
    -0.52
    []
    
    -0.52
    SizeMode
    -0.51
    ExtendWith
    -0.50
    wanza
    -0.50
    ++)
    
    -0.49
    POSITIVE LOGITS
     toilet
    1.32
     toilets
    1.29
     Toilet
    1.18
     restroom
    1.13
    toilet
    1.12
    Toilet
    1.09
     bathroom
    1.03
     restrooms
    1.02
     toilettes
    1.00
     bathrooms
    0.96
    Activations Density 0.116%

    No Known Activations