© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 14817
    Prev
    Next
    INDEX
    Explanations

    references to circuits and related electronic components

    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
    Примітки
    -0.71
    PointerException
    -0.71
    原始内容存档于
    -0.64
    Personensuche
    -0.63
     fert
    -0.63
     Kali
    -0.62
    Хьажоргаш
    -0.62
    InjectAttribute
    -0.62
    ($__
    -0.61
    евра
    -0.61
    POSITIVE LOGITS
     circuit
    1.38
     Circuit
    1.30
    Circuit
    1.14
    circuit
    1.12
     CIRCUIT
    1.11
     circuits
    1.05
     circuitry
    0.93
     Circuits
    0.91
     circuitos
    0.89
    CUIT
    0.85
    Activations Density 0.060%

    No Known Activations