© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3979
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific coding elements related to programming and API interactions

    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
    web
    -0.49
     escapar
    -0.47
     web
    -0.44
    Web
    -0.42
     casó
    -0.41
     ruote
    -0.39
     règle
    -0.38
    utet
    -0.37
     Web
    -0.36
    ิลปะ
    -0.36
    POSITIVE LOGITS
    ValueStyle
    1.11
    #+#
    0.97
    ViewImports
    0.84
     INTERESAR
    0.82
    WebServlet
    0.81
     surla
    0.81
     unknownFields
    0.80
    StoreMessageInfo
    0.79
     للاسماء
    0.78
     الحره
    0.78
    Activations Density 2.553%

    No Known Activations