© 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. 5317
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to constitutional law and judicial processes

    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
     Krause
    -0.70
     raping
    -0.69
     Italijanski
    -0.69
     нашли
    -0.68
    早い
    -0.67
     eleva
    -0.67
     decomposed
    -0.66
     destina
    -0.65
     ratify
    -0.65
    theoremstyle
    -0.65
    POSITIVE LOGITS
     deſt
    0.69
     raiſ
    0.64
     itſelf
    0.64
    GHIJKLM
    0.64
     circum
    0.64
    Воз
    0.62
     tranſ
    0.62
    cknow
    0.62
     poffe
    0.62
     atsi
    0.61
    Activations Density 4.388%

    No Known Activations