© 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 - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 12534
    Prev
    Next
    INDEX
    Explanations

    elements related to legal or judicial terms, particularly in the context of arrests and charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    彼の
    -1.52
     ň
    -1.37
     hänen
    -1.30
    His
    -1.21
    his
    -1.21
     honom
    -1.17
    彼が
    -1.16
     his
    -1.13
     그의
    -1.12
     seinem
    -1.05
    POSITIVE LOGITS
     he
    2.52
     он
    0.63
     הוא
    0.49
    Przypisy
    0.45
    новништво
    0.42
     سكانية
    0.42
     він
    0.42
     hè
    0.40
    Hochspringen
    0.40
    setContentView
    0.38
    Activations Density 0.522%

    No Known Activations