© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2042
    Prev
    Next
    INDEX
    Explanations

    concepts related to political and social issues, particularly regarding rights and governance

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

    followed by negative consequences

    np_acts-logits-general · gemini-2.0-flash

    negative consequences or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.74
     myſelf
    -0.68
     chofe
    -0.66
     ſeveral
    -0.65
     pleaſure
    -0.65
     houſe
    -0.62
     purpoſe
    -0.62
     Jefus
    -0.60
     transfieras
    -0.59
     Monfieur
    -0.59
    POSITIVE LOGITS
     threatened
    0.93
     jeopardi
    0.89
     jeopardy
    0.84
     compromised
    0.81
     Threatened
    0.80
     endangered
    0.77
     undermined
    0.70
     disrupted
    0.66
     impaired
    0.64
     menac
    0.64
    Activations Density 0.368%

    No Known Activations