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
    6. 12549
    Prev
    Next
    INDEX
    Explanations

    references to dictionaries and legal texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
    istoitu
    -0.49
    bewerken
    -0.42
     оригіналу
    -0.41
     związane
    -0.41
    Legături
    -0.39
     Arquivado
    -0.39
     successful
    -0.38
     to
    -0.37
    敬
    -0.37
    lamydia
    -0.36
    POSITIVE LOGITS
     encyclopedia
    0.83
    出版年
    0.78
    sizeCache
    0.77
    <?
    0.72
     intptr
    0.70
    StructEnd
    0.69
    وعة
    0.67
    lismo
    0.66
    jsii
    0.65
     encyclo
    0.63
    Activations Density 0.568%

    No Known Activations