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. 7-GEMMASCOPE-RES-16K
    6. 9526
    Prev
    Next
    INDEX
    Explanations

    references to clothing and dressing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.97
     الحره
    -0.92
    ismet
    -0.89
    ]){
    
    -0.87
    UnsafeEnabled
    -0.81
    ValueGenerated
    -0.80
    ]]
    
    -0.76
    })));
    -0.75
    存于互联网档案馆
    -0.75
    }]
    
    -0.74
    POSITIVE LOGITS
     clothes
    1.44
     dress
    1.43
     clothing
    1.35
     Clothes
    1.29
     Dress
    1.25
     dresses
    1.19
    dress
    1.19
    Dress
    1.16
    clothes
    1.16
    Clothes
    1.15
    Activations Density 0.117%

    No Known Activations