© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 53242
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    whether prosecute or charge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chham
    -0.48
    ftagPool
    -0.42
    AndEndTag
    -0.41
     femmin
    -0.41
     esfor
    -0.40
     adquirido
    -0.40
    NamedQuery
    -0.40
     raggi
    -0.40
     Tid
    -0.40
     desta
    -0.39
    POSITIVE LOGITS
    addPreferredGap
    0.44
    Revenir
    0.41
     <<<<<<<<<<<<<<
    0.40
    addGap
    0.39
     criminal
    0.39
    IVEREF
    0.37
     Criminal
    0.37
    httphttps
    0.37
    PerformLayout
    0.37
     CRIMINAL
    0.37
    Activations Density 0.045%

    No Known Activations