© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 37-GEMMASCOPE-RES-16K
    11. 3308
    Prev
    Next
    INDEX
    Explanations

    instances of the word "would" and variations of "did"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.49
    rawDesc
    -0.44
    IntoConstraints
    -0.40
     Meksiku
    -0.38
     gelingt
    -0.35
     tartalmaz
    -0.35
    ことができる
    -0.34
    EndProject
    -0.34
    PreInfinity
    -0.32
     Ibid
    -0.31
    POSITIVE LOGITS
     like
    0.88
     gerne
    0.70
     gärna
    0.67
     wager
    0.66
     LIKE
    0.65
    Rather
    0.65
     rather
    0.63
     gjerne
    0.63
     love
    0.61
     Rather
    0.60
    Activations Density 0.144%

    No Known Activations