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. 20-GEMMASCOPE-RES-16K
    6. 10144
    Prev
    Next
    INDEX
    Explanations

    the opening of a text or a new section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    After capitalized words

    np_acts-logits-general · gemini-2.0-flash

    sequence specific manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onAttach
    -0.80
     myſelf
    -0.74
     henceforth
    -0.70
     Efq
    -0.70
     betweenstory
    -0.70
    raszam
    -0.69
     thereupon
    -0.69
     ویکی‌پدیا
    -0.67
    الحياه
    -0.65
    InjectAttribute
    -0.64
    POSITIVE LOGITS
    </h1>
    0.65
     }
    
    0.63
    </h4>
    0.63
    }{*}{
    0.63
    {...
    0.62
    ")]
    
    0.60
     ‘
    0.60
    )))
    
    0.60
    </h2>
    0.59
    ]))
    
    0.59
    Activations Density 0.055%

    No Known Activations