© 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. 13273
    Prev
    Next
    INDEX
    Explanations

    references to political figures and administrations

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

    US presidential administrations

    np_acts-logits-general · gemini-2.0-flash

    presidential administrations

    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
    >*/
    -0.56
    uxxxx
    -0.46
     endblock
    -0.45
    Synopsis
    -0.44
     bandoulière
    -0.43
    qus
    -0.42
    동
    -0.42
    tirol
    -0.42
    BufferException
    -0.41
    chas
    -0.41
    POSITIVE LOGITS
     administration
    1.78
     Administration
    1.46
    administration
    1.36
     admin
    1.33
     administrations
    1.29
     ADMINISTRATION
    1.29
    Administration
    1.25
     Admin
    1.17
     administración
    1.08
     administra
    1.08
    Activations Density 0.163%

    No Known Activations