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

    Neuronpedia

    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. 3-GEMMASCOPE-RES-16K
    11. 9623
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to deception or manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adapta
    -0.72
     inspira
    -0.67
     сделали
    -0.65
     нашли
    -0.63
     делают
    -0.62
     orienta
    -0.62
     coinciden
    -0.62
     representa
    -0.61
     interpreta
    -0.61
     combina
    -0.60
    POSITIVE LOGITS
     poffe
    0.85
     raiſ
    0.80
    MethodManager
    0.74
     atsi
    0.73
     deſt
    0.72
    AndEndTag
    0.70
    %";
    0.69
    cknow
    0.68
    etzal
    0.68
     herum
    0.67
    Activations Density 1.154%

    No Known Activations