© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 5193
    Prev
    Next
    INDEX
    Explanations

    the word "In" and its variations, which indicate context or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.84
     myſelf
    -0.81
     pleaſure
    -0.80
     themſelves
    -0.75
     müſſen
    -0.75
     zoude
    -0.74
     purpoſe
    -0.72
     Geſch
    -0.72
     Geiſt
    -0.72
     ſta
    -0.71
    POSITIVE LOGITS
     in
    2.20
     In
    2.08
     IN
    1.91
    In
    1.82
    in
    1.48
    getIn
    1.31
     în
    1.27
     isIn
    1.19
    isIn
    1.18
    IN
    1.17
    Activations Density 1.185%

    No Known Activations