© 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. 24-GEMMASCOPE-RES-16K
    11. 4903
    Prev
    Next
    INDEX
    Explanations

    themes related to personal struggles and emotional challenges

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

    emotions or inner states

    np_acts-logits-general · gemini-2.0-flash

    abstract concepts or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     navires
    -0.93
     gouvernements
    -0.82
     générations
    -0.80
     exemplaires
    -0.79
     vaisseaux
    -0.78
     âmes
    -0.75
     lèvres
    -0.74
     prisonniers
    -0.74
     journaux
    -0.73
     épaules
    -0.73
    POSITIVE LOGITS
     fears
    0.91
     wishes
    0.87
     hopes
    0.85
     desires
    0.82
     worries
    0.81
     concerns
    0.80
     stresses
    0.75
     claims
    0.72
     risks
    0.71
     regrets
    0.69
    Activations Density 0.860%

    No Known Activations