© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 5818
    Prev
    Next
    INDEX
    Explanations

    prepositions and their usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insertions
    -0.42
     OTHERS
    -0.42
     apron
    -0.42
     slike
    -0.42
     spots
    -0.42
     ferons
    -0.41
     ulter
    -0.39
     bir
    -0.39
    etc
    -0.38
     superficial
    -0.38
    POSITIVE LOGITS
     the
    0.73
     either
    0.59
     our
    0.59
     both
    0.58
     another
    0.56
     betrekking
    0.54
    的是
    0.52
    verwijspagina
    0.50
     behalf
    0.50
     his
    0.50
    Activations Density 1.253%

    No Known Activations