© 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. 16-GEMMASCOPE-RES-16K
    6. 13390
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court proceedings and settlements

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

    negotiations or agreements

    np_acts-logits-general · gemini-2.0-flash

    settle or negotiate peace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewGuid
    -0.44
     noches
    -0.43
    gypti
    -0.43
     scoper
    -0.42
    canic
    -0.42
     unlucky
    -0.42
    viewDidLoad
    -0.41
     tyranny
    -0.40
     mạch
    -0.39
     supporting
    -0.39
    POSITIVE LOGITS
     negotiated
    1.03
     concili
    0.92
     concessions
    0.92
     negotiations
    0.86
    negoti
    0.86
    setVerticalGroup
    0.84
     concession
    0.83
     negotiate
    0.82
     voluntary
    0.81
     conciliation
    0.81
    Activations Density 0.515%

    No Known Activations