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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-GEMMASCOPE-RES-16K
    6. 6739
    Prev
    Next
    INDEX
    Explanations

    proper nouns and entities related to politics and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     considérons
    -0.53
     للاسماء
    -0.51
     פשוט
    -0.48
    户
    -0.44
    diers
    -0.44
    thritis
    -0.43
    insee
    -0.43
     putra
    -0.42
     Kild
    -0.42
    dung
    -0.42
    POSITIVE LOGITS
    ad
    1.77
    ads
    1.39
     Ad
    1.25
    ada
    1.22
    AD
    1.17
    Ad
    1.17
    ADA
    1.15
     ad
    1.09
    ady
    1.06
    ade
    1.06
    Activations Density 2.418%

    No Known Activations