© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2988
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions in relation to objects and subjects in sentences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    antası
    -0.52
     vertes
    -0.50
     Signalez
    -0.50
    voorbeeld
    -0.49
    ness
    -0.48
    ėj
    -0.47
    TotalCount
    -0.47
    ťaž
    -0.47
    pherals
    -0.46
    getUsers
    -0.46
    POSITIVE LOGITS
     dei
    0.76
     della
    0.62
     о
    0.52
     delle
    0.45
     со
    0.41
     DELLA
    0.41
    "]=
    0.41
    awaiter
    0.40
     Dei
    0.39
     quoique
    0.38
    Activations Density 0.090%

    No Known Activations