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

    Neuronpedia

    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. 130
    Prev
    Next
    INDEX
    Explanations

    references to legal regulations and compliance policies

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

    Legal and regulatory compliance

    np_acts-logits-general · gemini-2.0-flash

    laws and regulations

    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
     theo
    -0.46
    stdc
    -0.43
    lise
    -0.42
    URANCE
    -0.42
     androidx
    -0.41
     himo
    -0.41
    ьаж
    -0.41
     menurut
    -0.40
    kehrt
    -0.39
    φαλ
    -0.39
    POSITIVE LOGITS
     vigente
    0.87
     applicable
    0.78
     governing
    0.77
    applicable
    0.77
     Roskov
    0.71
     APPLICABLE
    0.70
    IonicModule
    0.69
     prohibiting
    0.68
    ParallelGroup
    0.64
     aplicable
    0.64
    Activations Density 0.759%

    No Known Activations