© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102372
    Prev
    Next
    INDEX
    Explanations

    terms related to evidence gathering and investigation in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    getStatusCode
    -0.38
    MediaStore
    -0.36
    crisy
    -0.36
     naturen
    -0.35
     Lokales
    -0.35
    様
    -0.35
    fulness
    -0.33
    Aktualisiert
    -0.33
    ColumnHeaders
    -0.33
    contentLoaded
    -0.33
    POSITIVE LOGITS
    Vidite
    0.56
     GenerationType
    0.52
     насељу
    0.51
     traced
    0.49
    Personensuche
    0.49
    Приятного
    0.48
     trace
    0.47
     <=",
    0.47
    Controllo
    0.46
     bağlantılar
    0.46
    Activations Density 0.025%

    No Known Activations