© 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 EvalsExportsAPI 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. 36094
    Prev
    Next
    INDEX
    Explanations

    references to arrest and imprisonment

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

    arrested, jailed, or banned

    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
     للاسماء
    -0.61
     initComponents
    -0.48
    onViewCreated
    -0.44
    WithFormat
    -0.44
    CloseOperation
    -0.44
     HasFactory
    -0.43
     bénéficiaire
    -0.43
    awakeFromNib
    -0.42
     entitlement
    -0.41
    zionalità
    -0.40
    POSITIVE LOGITS
    üttel
    0.45
    ().__
    0.42
    GenerationType
    0.40
    kegaard
    0.38
    magnetic
    0.38
    endphp
    0.37
    oglobulin
    0.37
     fileSize
    0.35
    diag
    0.35
     Monographs
    0.35
    Activations Density 0.027%

    No Known Activations