© 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. 2991
    Prev
    Next
    INDEX
    Explanations

    references to incarceration and its impact on individuals or communities

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

    words and phrases expressing duration, passage of time, or long-term continuity.

    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
    expandindo
    -0.68
    bootstrapcdn
    -0.64
    \{\\
    -0.58
     utafitiHapana
    -0.51
    CloseOperation
    -0.49
     heuti
    -0.48
     BoxFit
    -0.47
     shalt
    -0.47
    oa̍t
    -0.47
     dagens
    -0.45
    POSITIVE LOGITS
     ever
    2.30
     since
    2.11
    since
    1.78
     depuis
    1.75
    ever
    1.66
     sejak
    1.64
     SINCE
    1.61
    Ever
    1.55
     Ever
    1.54
    Since
    1.50
    Activations Density 0.436%

    No Known Activations