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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15226
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court proceedings and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Actions regarding limitations or rules

    np_acts-logits-general · gemini-2.0-flash

    restrictions lifted or imposed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.51
    Portail
    -0.49
     jardins
    -0.47
    хта
    -0.46
     aventures
    -0.46
    Способ
    -0.45
     sotto
    -0.45
    صح
    -0.45
    haga
    -0.45
     liten
    -0.44
    POSITIVE LOGITS
     imposed
    1.05
     imposition
    0.92
    imposed
    0.82
     lifted
    0.81
    解除
    0.81
     removal
    0.79
     enforced
    0.72
     Removal
    0.72
     applied
    0.72
     removing
    0.71
    Activations Density 0.717%

    No Known Activations