© 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. 31-GEMMASCOPE-RES-131K
    6. 65606
    Prev
    Next
    INDEX
    Explanations

    terms related to liability and claims in a contract context

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

    liability for injury or damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hopefully
    -0.41
     ganger
    -0.39
     gâ
    -0.38
    SUCCEEDED
    -0.37
    Herzliche
    -0.36
    indest
    -0.35
     Britain
    -0.35
    Britain
    -0.34
     certeza
    -0.34
    Hopefully
    -0.34
    POSITIVE LOGITS
    WebVitals
    0.63
    reportWebVitals
    0.62
     misuse
    0.61
    endregion
    0.61
     nahilalakip
    0.60
    InstrumentedTest
    0.60
     consumables
    0.57
    verwijspagina
    0.56
     <>",
    0.56
     resourceCulture
    0.56
    Activations Density 0.021%

    No Known Activations