© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 13326
    Prev
    Next
    INDEX
    Explanations

    legal terms related to jury verdicts and court decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     effort
    -0.49
     post
    -0.49
    multer
    -0.49
     plug
    -0.46
     Q
    -0.46
     kín
    -0.46
     Ever
    -0.43
     plugs
    -0.42
     sup
    -0.42
    isome
    -0.42
    POSITIVE LOGITS
     provisoire
    0.85
     الحره
    0.84
    mybatisplus
    0.82
     unanimously
    0.75
     decreed
    0.74
     definitivo
    0.74
     decrees
    0.73
    CloseOperation
    0.71
     decree
    0.70
    TestingModule
    0.70
    Activations Density 0.859%

    No Known Activations