© 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. 31-GEMMASCOPE-RES-16K
    11. 2937
    Prev
    Next
    INDEX
    Explanations

    phrases related to existence and prior actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    words and phrases indicating that something has already occurred or been completed.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Administrativna
    -0.43
     Reverso
    -0.33
    xtext
    -0.33
    IntoConstraints
    -0.32
    次回は
    -0.31
    𝟹
    -0.30
    に至
    -0.30
     Infórmanos
    -0.29
    richTextPanel
    -0.29
     Winaray
    -0.29
    POSITIVE LOGITS
     already
    4.25
    already
    3.81
     Already
    3.81
    Already
    3.66
     ALREADY
    3.27
     уже
    2.94
     이미
    2.89
     allerede
    2.86
     redan
    2.84
    すでに
    2.78
    Activations Density 1.883%

    No Known Activations