© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5994
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal cases and their implications

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

    words and phrases related to institutional or bureaucratic contexts, particularly around the UK audit market, legal proceedings, and academic/professional careers.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    OGND
    -0.70
     transfieras
    -0.68
     صوتيه
    -0.68
    
    -0.66
    sizeCache
    -0.64
    ViewImports
    -0.63
    IUrlHelper
    -0.63
    majánló
    -0.61
     defaultstate
    -0.59
    Tembelea
    -0.59
    POSITIVE LOGITS
    真
    0.39
    reactstrap
    0.35
    玉
    0.35
    URS
    0.33
    “
    0.33
     정
    0.33
     
    0.32
    Phil
    0.32
    首先
    0.31
    문
    0.31
    Activations Density 0.685%

    No Known Activations