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. 16-GEMMASCOPE-RES-16K
    6. 13041
    Prev
    Next
    INDEX
    Explanations

    structured data or code syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.90
    Vidite
    -0.86
     للمعارف
    -0.73
     <>",
    -0.72
    AsUp
    -0.70
     Roskov
    -0.70
     дописавши
    -0.67
    Chham
    -0.66
     Италијани
    -0.66
     виправивши
    -0.66
    POSITIVE LOGITS
    ↵
    2.17
    ↵↵
    1.58
    1.29
    ↵↵↵
    0.97
    </h3>
    0.91
    </h4>
    0.88
    </h2>
    0.83
     
    
    0.83
    ]),
    
    0.80
    </strong>
    0.79
    Activations Density 1.380%

    No Known Activations