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. 5-GEMMASCOPE-RES-16K
    6. 4355
    Prev
    Next
    INDEX
    Explanations

    references to political figures and entities in the context of Malaysia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WillAppear
    -0.77
     nahilalakip
    -0.76
    UnknownFieldSet
    -0.74
    NameInMap
    -0.72
    Datuak
    -0.71
    ंदीखरीदारी
    -0.70
     propOrder
    -0.70
     onCreateView
    -0.70
    étit
    -0.69
     initComponents
    -0.69
    POSITIVE LOGITS
    layui
    0.47
     telinga
    0.43
     faker
    0.41
    ransition
    0.41
    trina
    0.40
     ͜ʖ
    0.40
    alba
    0.40
     Merkel
    0.39
     Buffett
    0.39
     Nadal
    0.39
    Activations Density 0.887%

    No Known Activations