© 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. 37-GEMMASCOPE-RES-16K
    11. 7772
    Prev
    Next
    INDEX
    Explanations

    phrases that express personal opinions or considerations about parenting and decision-making

    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
    <eos>
    -0.43
     is
    -0.31
     Verhält
    -0.30
     halben
    -0.30
     Bedürfn
    -0.30
     also
    -0.30
     stolz
    -0.29
     Aspekte
    -0.29
     (
    -0.28
      
    -0.28
    POSITIVE LOGITS
    niſſe
    1.38
     ſche
    1.34
     kasarigan
    1.32
    ſelves
    1.32
     ſind
    1.32
     ſch
    1.30
    <unused52>
    1.29
    <unused14>
    1.29
    [@BOS@]
    1.29
    <unused3>
    1.28
    Activations Density 6.753%

    No Known Activations