© 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. 14-GEMMASCOPE-RES-16K
    11. 13478
    Prev
    Next
    INDEX
    Explanations

    instances of legislative and governmental language related to policy and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.45
    脚注の使い方
    -0.44
    USTR
    -0.42
     Sonora
    -0.41
    Américaine
    -0.40
    amazonaws
    -0.40
     Hsi
    -0.40
    fäl
    -0.40
    ånga
    -0.39
    phthal
    -0.39
    POSITIVE LOGITS
    الإنجليزية
    0.82
     oprot
    0.81
     encouragement
    0.80
     Encourage
    0.78
    __':
    0.77
     soutien
    0.75
     encourage
    0.74
    ')['
    0.73
    Helping
    0.72
     encourag
    0.72
    Activations Density 0.418%

    No Known Activations