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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 4264
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and legal agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    herzog
    -0.68
     initComponents
    -0.67
    RemoteException
    -0.62
     Outsourcing
    -0.62
     فريبيس
    -0.61
    hbase
    -0.58
     textStatus
    -0.58
    BagLayout
    -0.57
    出版年
    -0.57
    ]")]
    -0.56
    POSITIVE LOGITS
     deposit
    1.64
     Deposit
    1.38
     deposits
    1.33
     DEPOSIT
    1.31
    deposit
    1.31
    Deposit
    1.30
     Deposits
    1.17
     security
    1.14
     DEPOS
    1.09
    Deposits
    1.08
    Activations Density 0.168%

    No Known Activations