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. 12-GEMMASCOPE-RES-16K__L0-22
    6. 1
    Prev
    Next
    INDEX
    Explanations

    the concept of remaining or residual elements in context.

    oai_token-act-pair · gpt-4oTriggered by @gulkoa
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.91
    uxxxx
    -0.86
     ddelweddau
    -0.83
    
    -0.82
     InputDecoration
    -0.81
    (!__
    -0.80
     ویکی‌پدیا
    -0.80
     صوتيه
    -0.80
    Билгалдахарш
    -0.80
     дописавши
    -0.78
    POSITIVE LOGITS
     remaining
    1.25
    残
    1.09
     residual
    1.01
     Remaining
    1.00
     remnant
    1.00
     sisa
    0.99
    remaining
    0.97
    Remaining
    0.97
    剩
    0.96
    に残
    0.92
    Activations Density 0.076%

    No Known Activations