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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 123208
    Prev
    Next
    INDEX
    Explanations

    terms related to cheating and fraud

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

    cheating and fraud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     AssemblyVersion
    -0.58
     dezelve
    -0.54
     ویکی‌پدی
    -0.54
    bildēt
    -0.54
    webElementXpaths
    -0.52
    gonic
    -0.51
     ujednoznacz
    -0.50
    calaureate
    -0.49
    partimento
    -0.48
     zoude
    -0.47
    POSITIVE LOGITS
     cheating
    0.64
    cheat
    0.62
     cheat
    0.62
    Cheat
    0.58
     Cheat
    0.51
     cheats
    0.49
    AddTagHelper
    0.43
     cheated
    0.39
     scand
    0.38
     ilegal
    0.36
    Activations Density 0.012%

    No Known Activations