© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15361
    Prev
    Next
    INDEX
    Explanations

    elements related to governance and political issues

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

    preceding "is" or "has"

    np_acts-logits-general · gemini-2.0-flash

    institutional or situational nouns followed by verbs

    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
     eigenvectors
    -0.82
     analogues
    -0.80
     embodiments
    -0.79
     wrappers
    -0.79
     examples
    -0.79
     signatures
    -0.78
     excuses
    -0.78
     analogs
    -0.77
     messengers
    -0.77
     successors
    -0.76
    POSITIVE LOGITS
     bénéfices
    0.60
     émissions
    0.60
     intérêts
    0.57
     coûts
    0.57
     standpoint
    0.56
     version
    0.55
     vérit
    0.54
     âmes
    0.53
     genoux
    0.53
     vœux
    0.53
    Activations Density 3.186%

    No Known Activations