© 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. 7321
    Prev
    Next
    INDEX
    Explanations

    text that discusses scholarly works and their theoretical frameworks, particularly in relation to social movements and political contexts

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

    Prepositions followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    explain to demonstrate

    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
    protoimpl
    -0.70
    Diweddarwch
    -0.63
    wann
    -0.62
     commerciaux
    -0.59
     controllare
    -0.58
     fermés
    -0.58
     définiti
    -0.58
     volontaire
    -0.57
     quelcon
    -0.56
     réaliste
    -0.55
    POSITIVE LOGITS
     interrog
    0.97
     interro
    0.85
     interrogation
    0.78
     challenge
    0.78
     situ
    0.76
     problem
    0.73
     probe
    0.71
     grapple
    0.71
     foreground
    0.70
     Situ
    0.69
    Activations Density 0.361%

    No Known Activations