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. 0-GEMMASCOPE-RES-16K
    6. 6804
    Prev
    Next
    INDEX
    Explanations

    specific programming terminology related to object properties and their descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ")));
    
    -1.22
     contextLoads
    -1.13
    )");
    
    -1.11
    ]]
    
    -1.09
    )";
    
    -1.09
    ]$}
    -1.07
    "):
    
    -1.05
    "])
    
    -1.04
    ]");
    -1.04
    "]);
    
    -1.03
    POSITIVE LOGITS
    Descriptor
    0.56
    발
    0.52
    ura
    0.50
    ural
    0.49
     bracket
    0.48
    配
    0.48
    INIT
    0.48
    sz
    0.48
     subsidiary
    0.48
    submenu
    0.48
    Activations Density 2.950%

    No Known Activations