Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 12262
    Prev
    Next
    INDEX
    Explanations

    mathematical terminologies and notation related to algebraic structures

    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
     ammi
    -0.51
    ExtendWith
    -0.51
    Obrázky
    -0.50
    localctx
    -0.47
    poko
    -0.47
     uchun
    -0.46
    abaikan
    -0.44
    Zitat
    -0.44
     splet
    -0.43
     agricoles
    -0.43
    POSITIVE LOGITS
     ModelExpression
    0.97
     Italijanski
    0.77
    bootstrapcdn
    0.67
     незавершена
    0.66
    tagHelperRunner
    0.66
    出版年
    0.66
    UserScript
    0.65
     function
    0.65
     Function
    0.64
    WriteBarrier
    0.63
    Activations Density 1.228%

    No Known Activations