© 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. 20-GEMMASCOPE-RES-16K
    11. 15867
    Prev
    Next
    INDEX
    Explanations

    associations and relationships between government actions and funding

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

    Prepositions followed by "the"

    np_acts-logits-general · gemini-2.0-flash

    preposition followed by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anything
    -0.58
    anything
    -0.51
     everything
    -0.49
     alles
    -0.48
    da
    -0.44
     ANYTHING
    -0.42
    ytick
    -0.41
    uk
    -0.41
     something
    -0.40
     things
    -0.40
    POSITIVE LOGITS
     فريبيس
    1.06
    CloseOperation
    0.88
     fubject
    0.80
     regeringen
    0.80
    بوابة
    0.78
     nahilalakip
    0.77
     صوتيه
    0.76
     ſtate
    0.72
    ]--;
    0.71
     myſelf
    0.71
    Activations Density 0.563%

    No Known Activations