© 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. 22-GEMMASCOPE-RES-16K
    11. 8313
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating relationships or contexts of movement and action

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

    Prepositions like "through" and "under"

    np_acts-logits-general · gemini-2.0-flash

    through, under, against, during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vermelhas
    -0.84
     brancas
    -0.80
     noastre
    -0.80
     nostru
    -0.76
     deoarece
    -0.74
     âgées
    -0.73
     suivantes
    -0.72
     înainte
    -0.71
     noastră
    -0.70
     vectorielles
    -0.69
    POSITIVE LOGITS
     the
    1.55
     its
    1.11
     a
    1.11
     both
    1.08
     their
    1.06
     an
    1.03
     either
    1.01
     whom
    0.99
     those
    0.98
     these
    0.97
    Activations Density 0.555%

    No Known Activations