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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 121888
    Prev
    Next
    INDEX
    Explanations

    topics related to current political issues and societal norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     kepad
    -0.60
     Infór
    -0.56
    +#+#
    -0.54
    colgante
    -0.54
     dioses
    -0.53
     inalámb
    -0.53
     desmotivaciones
    -0.52
     expérimentés
    -0.52
    AllAfrica
    -0.52
    ktır
    -0.51
    POSITIVE LOGITS
     polarization
    0.46
     Trump
    0.46
     noqa
    0.46
     impeachment
    0.44
     pandemic
    0.43
     climate
    0.42
     Charlottesville
    0.40
     political
    0.40
    ArrowToggle
    0.39
     covid
    0.39
    Activations Density 0.154%

    No Known Activations