© 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. 14-GEMMASCOPE-RES-16K
    6. 7269
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to evidence, particularly focusing on material facts and their relevance in legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригіналу
    -0.61
    reportWebVitals
    -0.60
     становника
    -0.58
     EconPapers
    -0.55
    rophes
    -0.55
     nawr
    -0.54
     cumplido
    -0.54
    ContextHolder
    -0.52
    олові
    -0.52
     sobres
    -0.51
    POSITIVE LOGITS
     houſe
    0.82
     ſtate
    0.74
     neceff
    0.70
     Monfieur
    0.69
     iſt
    0.67
     reaſon
    0.67
     ſte
    0.66
     Houſe
    0.63
     purpoſe
    0.62
     ſche
    0.62
    Activations Density 1.046%

    No Known Activations