© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12173
    Prev
    Next
    INDEX
    Explanations

    references to political ideologies, particularly focused on conservatism and liberalism

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

    Political ideologies and affiliations

    np_acts-logits-general · gemini-2.0-flash

    political conservatism and fascism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    UALA
    -0.50
    Fermi
    -0.48
     numberWith
    -0.47
    ImageContext
    -0.46
    Miss
    -0.45
     NOK
    -0.45
    Match
    -0.44
    Qual
    -0.43
     Najib
    -0.43
     fam
    -0.43
    POSITIVE LOGITS
     liberal
    0.56
    liberal
    0.55
     liberdade
    0.54
     paham
    0.54
    SuppressLint
    0.54
     teorías
    0.53
     sayap
    0.53
     liberalism
    0.53
     tendencias
    0.52
     idéia
    0.51
    Activations Density 0.368%

    No Known Activations