© 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. 16-GEMMASCOPE-RES-16K
    11. 13993
    Prev
    Next
    INDEX
    Explanations

    references to manipulation and staged events, particularly in political or controversial contexts

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

    Intentional/deliberate actions

    np_acts-logits-general · gemini-2.0-flash

    deliberately planned or staged actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.66
     myſelf
    -0.66
     égale
    -0.64
     disambiguazione
    -0.62
     neuve
    -0.61
     pleaſure
    -0.61
     reunited
    -0.60
    %)$
    -0.59
     dépasse
    -0.59
     <>",
    -0.58
    POSITIVE LOGITS
     deliberately
    0.96
    故意
    0.93
     intentionally
    0.91
     purposely
    0.88
     purposefully
    0.79
     fake
    0.78
    あえて
    0.76
    わざ
    0.74
     sengaja
    0.69
     feign
    0.68
    Activations Density 0.650%

    No Known Activations