© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 16171
    Prev
    Next
    INDEX
    Explanations

    phrases related to decline and transition in life stages or career paths

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

    ending or finishing

    np_acts-logits-general · gemini-2.0-flash

    reign of terror to an end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.77
     myſelf
    -0.76
    Приятного
    -0.72
     initComponents
    -0.70
    ſelf
    -0.70
    XmlAccessType
    -0.70
     AssemblyTitle
    -0.69
    :✨
    -0.65
     الحره
    -0.65
    ſelves
    -0.64
    POSITIVE LOGITS
     ended
    1.36
     end
    1.32
     ends
    1.27
     ending
    1.22
     finished
    1.22
    終了
    1.11
     Ends
    1.11
    结束
    1.10
     finish
    1.09
     END
    1.08
    Activations Density 0.305%

    No Known Activations